Adín Ramírez Rivera

• Tan, Martine Hjelkrem; Aasan, Marius; Chakraborty, Rwiddhi; Arteaga, Gabriel Yanci; Choi, Changkyu & Rivera, Adín Ramírez (2026). Suppressing Non-Semantic Noise in Masked Image Modeling Representations. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 19319–19329. doi: https:/openaccess.thecvf.com/content/CVPR2026/papers/Hjelkrem-Tan_Suppressing_Non-Semantic_Noise_in_Masked_Image_Modeling_Representations_CVPR_2026_paper.pdf. Full text in Research Archive Show summary

  Masked Image Modeling (MIM) has become a ubiquitous self-supervised vision paradigm. In this work, we show that MIM objectives cause the learned representations to retain non-semantic information, which ultimately hurts performance during inference. We introduce a model-agnostic score for semantic invariance using Principal Component Analysis (PCA) on real and synthetic non-semantic images. Based on this score, we propose a simple method, Semantically Orthogonal Artifact Projection (SOAP), to directly suppress non-semantic information in patch representations, leading to consistent improvements in zero-shot performance across various MIM-based models. SOAP is a post-hoc suppression method, requires zero training, and can be attached to any model as a single linear head.

• Tan, Martine Hjelkrem; Aasan, Marius; Arteaga, Gabriel Yanci & Rivera, Adín Ramírez (2026). SPoT: Subpixel Placement of Tokens in Vision Transformers. Transactions on Machine Learning Research (TMLR). 3(26). Full text in Research Archive Show summary

  Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose Subpixel Placement of Tokens (SPoT), a novel tokenization strategy that positions tokens continuously within images, effectively sidestepping grid-based limitations. With our proposed oracle-guided search, we uncover substantial performance gains achievable with ideal subpixel token positioning, drastically reducing the number of tokens necessary for accurate predictions during inference. SPoT provides a new direction for flexible, efficient, and interpretable ViT architectures, redefining sparsity as a strategic advantage rather than an imposed limitation.

• Galliamov, Karim; Kazmi, Syed M Ahsan; Khan, Adil Mehmood & Rivera, Adín Ramírez (2026). Concepts' Information Bottleneck Models. International Conference on Learning Representations (ICLR). doi: https:/openreview.net/forum?id=JGIYfwaNpT. Full text in Research Archive Show summary

  Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer, yet they often suffer reduced accuracy and concept leakage that undermines faithfulness. We introduce an explicit Information Bottleneck regularizer on the concept layer that penalizes I(X; C) while preserving task-relevant information in I(C; Y ), encouraging minimal-sufficient concept representations. We derive two practical variants (a variational objective and an entropy-based surrogate) and integrate them into standard CBM training without architectural changes or additional supervision. Evaluated across six CBM families and three benchmarks, the IB-regularized models consistently outperform their vanilla counterparts. Information-plane analyses further corroborate the intended behavior. These results indicate that enforcing a minimal-sufficient concept bottleneck improves both predictive performance and the reliability of concept-level interventions. The proposed regularizer offers a theoretic-grounded, architecture-agnostic path to more faithful and intervenable CBMs, resolving prior evaluation inconsistencies by aligning training protocols and demonstrating robust gains across model families and datasets.

• Arteaga, Gabriel Yanci; Aasan, Marius; Chakraborty, Rwiddhi; Tan, Martine Hjelkrem; Silva, Thalles & Kampffmeyer, Michael [Show all 7 contributors for this article] (2026). Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning. International Conference on Learning Representations (ICLR). doi: https:/openreview.net/forum?id=fVJEWdwvLO. Full text in Research Archive Show summary

  Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This undermines their central purpose—providing diverse and informative targets to guide encoders toward rich representations—and has led practitioners to over-parameterize prototype sets or add ad-hoc regularizers, which mitigate symptoms rather than address the root cause. We empirically trace the collapse to the joint optimization of encoders and prototypes, which encourages a type of shortcut learning: early in training prototypes drift toward redundant representations that minimize loss without necessarily enhancing representation diversity. To break the joint optimization, we introduce a fully decoupled training strategy that learns prototypes and encoders under separate objectives. Concretely, we model prototypes as a Gaussian mixture updated with an online EM-style procedure, independent of the encoder’s loss. This simple yet principled decoupling eliminates prototype collapse without explicit regularization and yields consistently diverse prototypes, which in several settings translate to improved downstream performance.

• Silva, Thalles; Pedrini, Helio & Rivera, Adín Ramírez (2025). Self-Organizing Visual Prototypes for Non-Parametric Representation Learning. Proceedings of Machine Learning Research (PMLR). 267, p. 55614–55630. Full text in Research Archive
• Bøe, Vilde Schulerud; Kleppe, Andreas; Foersch, Sebastian; Wagner, Daniel-Christoph; Busund, Lill-Tove Rasmussen & Rivera, Adín Ramírez (2025). Low-Rank Adaptations for increased Generalization in Foundation Model features. Proceedings of Machine Learning Research (PMLR). doi: https:/openreview.net/pdf?id=0BJTRUVDf4. Full text in Research Archive Show summary

  For foundation models (FMs) to truly advance computational pathology, they must deliver consistent and reliable predictions under diverse, unseen test conditions. Without such robustness, clinical trust and widespread adoption remain out of reach. Although many FMs for histopathology now exist, they have to our knowledge not been systematically tested for robustness by external researchers on independent datasets. In this study, we evaluate the robustness of foundation model features on three separate histopathology datasets and find that their performance drops on external data. Our analysis also reveals that these models often encode dataset-specific information, limiting their generalizability. To address this issue, we train a Weight-Decomposed Low-Rank Adaptation (DoRA) with strong data augmentations to improve feature robustness. Our experiments show that models trained with this adapter exhibit fewer signs of dataset-specific information and may generate more robust features across domains. These results highlight the need for robustness testing and encourage incorporating robustness considerations into the development, training, and tuning of FMs for histopathology. The code for this work will be available at https://github.com/dsb-ifi/DoRA-for-FM-robustness

• Aasan, Marius; Tan, Martine Hjelkrem; Catalano, Nico; Choi, Changkyu & Rivera, Adín Ramírez (2025). Differentiable Hierarchical Visual Tokenization. Advances in Neural Information Processing Systems. ISSN 1049-5258. 38. doi: 10.52202/085713-2930. Full text in Research Archive Show summary

  Vision Transformers rely on fixed patch tokens that ignore the spatial and semantic structure of images. In this work, we introduce an end-to-end differentiable tokenizer that adapts to image content with pixel-level granularity while remaining backward-compatible with existing architectures for retrofitting pretrained models. Our method uses hierarchical model selection with information criteria to provide competitive performance in both image-level classification and dense-prediction tasks, and even supports out-of-the-box raster-to-vector conversion.

• Aasan, Marius & Rivera, Adín Ramírez (2025). Pixel-Level Predictions with Embedded Lookup Tables. In Jenssen, Robert & Bach, Kerstin (Ed.), Proceedings of the Symposium of the Norwegian AI Society 2025. CEUR-WS. p. 49–59. Full text in Research Archive Show summary

  Pixel-level prediction tasks inherently face constraints imposed by image resolution and the number of prediction classes. As image resolutions and dimensionalities increase, these constraints lead to significant memory bottlenecks when explicitly modeling high-dimensional embeddings for each individual pixel. Addressing these bottlenecks requires the development of alternative, more efficient representations to facilitate continued progress in the field. In this work, we discuss Embedded Lookup Tables (ELUTs) with indexed segmentation maps as an alternative data structure for more memory efficient representations in image processing. We show that ELUTs are inherently compatible with cost functionals and metrics for pixel-level prediction tasks with a significant reduction in memory overhead.

• Aasan, Marius; Kolbjørnsen, Odd; Solberg, Anne H Schistad & Rivera, Adín Ramírez (2025). A Spitting Image: Modular Superpixel Tokenization in Vision Transformers. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 15641, p. 124–142. doi: 10.1007/978-3-031-93806-1_11. Full text in Research Archive Show summary

  Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and feature extraction; a shift from contemporary approaches where these are treated as an undifferentiated whole. Using on-line content-aware tokenization and scale- and shape-invariant positional embeddings, we perform experiments and ablations that contrast our approach with patch-based tokenization and randomized partitions as baselines. We show that our method significantly improves the faithfulness of attributions, gives pixel-level granularity on zero-shot unsupervised dense prediction tasks, while maintaining predictive performance in classification tasks. Our approach provides a modular tokenization framework commensurable with standard architectures, extending the space of ViTs to a larger class of semantically-rich models.

• Silva, Thalles; Pedrini, Helio & Rivera, Adín Ramírez (2024). Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features. Proceedings of Machine Learning Research (PMLR). doi: 10.48550/arXiv.2407.17486. Full text in Research Archive
• Silva, Thalles; Pedrini, Helio & Rivera, Adín Ramírez (2023). Self-supervised Learning of Contextualized Local Visual Embeddings. In Cho, Minsu & Ham, Bumsub (Ed.), 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350307443. p. 177–186. doi: 10.1109/ICCVW60793.2023.00025. Full text in Research Archive Show summary

  We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks. CLoVE deviates from current methods and optimizes a single loss function that operates at the level of contextualized local embeddings learned from output feature maps of convolution neural network (CNN) encoders. To learn contextualized embeddings, CLoVE proposes a normalized mult-head self-attention layer that combines local features from different parts of an image based on similarity. We extensively benchmark CLoVE’s pre-trained representations on multiple datasets. CLoVE reaches state-of-the-art performance for CNN-based architectures in 4 dense prediction downstream tasks, including object detection, instance segmentation, keypoint detection, and dense pose estimation. Code: https://github.com/sthalles/CLoVE.

• Souza, Bruno Cesar de Oliveira; Aasan, Marius; Pedrini, Helio & Rivera, Adín Ramírez (2023). SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering. In Cho, Minsu & Ham, Bumsub (Ed.), 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350307443. p. 4642–4647. doi: 10.1109/ICCVW60793.2023.00499. Full text in Research Archive Show summary

  The intersection of vision and language is of major interest due to the increased focus on seamless integration between recognition and reasoning. Scene graphs (SGs) have emerged as a useful tool for multimodal image analysis, showing impressive performance in tasks such as Visual Question Answering (VQA). In this work, we demonstrate that despite the effectiveness of scene graphs in VQA tasks, current methods that utilize idealized annotated scene graphs struggle to generalize when using predicted scene graphs extracted from images. To address this issue, we introduce the SelfGraphVQA framework. Our approach extracts a scene graph from an input image using a pretrained scene graph generator and employs semantically-preserving augmentation with self-supervised techniques. This method improves the utilization of graph representations in VQA tasks by circumventing the need for costly and potentially biased annotated data. By creating alternative views of the extracted graphs through image augmentations, we can learn joint embeddings by optimizing the informational content in their representations using an un-normalized contrastive approach. As we work with SGs, we experiment with three distinct maximization strategies: node-wise, graph-wise, and permutation-equivariant regularization. We empirically showcase the effectiveness of the extracted scene graph for VQA and demonstrate that these approaches enhance overall performance by highlighting the significance of visual information. This offers a more practical solution for VQA tasks that rely on SGs for complex reasoning questions.

• Kenfack, Patrik; Rivera, Adín Ramírez; Khan, Adil & Mazzara, Manuel (2023). Learning Fair Representations through Uniformly Distributed Sensitive Attributes. In McDaniel, Patrick & Papernot, Nicolas (Ed.), 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665462990. doi: 10.1109/SaTML54575.2023.00014. Full text in Research Archive Show summary

  Machine Learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's lives, ensuring their fairness is critical. One approach to mitigate possible unfairness of ML models is to map the input data into a less-biased new space by means of training the model on fair representations. Several methods based on adversarial learning have been proposed to learn fair representation by fooling an adversary in predicting the sensitive attribute (e.g., gender or race). However, adversarial-based learning can be too difficult to optimize in practice; besides, it penalizes the utility of the representation. Hence, in this research effort we train bias-free representations from the input data by inducing a uniform distribution over the sensitive attributes in the latent space. In particular, we propose a probabilistic framework that learns these representations by enforcing the correct reconstruction of the original data, plus the prediction of the attributes of interest while eliminating the possibility of predicting the sensitive ones. Our method leverages the inability of Deep Neural Networks (DNNs) to generalize when trained on a noisy label space to regularize the latent space. We use a network head that predicts a noisy version of the sensitive attributes in order to increase the uncertainty of their predictions at test time. Our experiments in two datasets demonstrated that the proposed model significantly improves fairness while maintaining the prediction accuracy of downstream tasks.

• Silva, Thalles & Rivera, Adín Ramírez (2022). Representation Learning via Consistent Assignment of Views to Clusters. In Hong, Jiman; Bures, Miroslav; Park, Juw Won & Cerny, Tomas (Ed.), SAC '22: Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing. Association for Computing Machinery (ACM). ISSN 9781450387132. doi: 10.1145/3477314.3507267. Full text in Research Archive
• Robles, Sandra; Gómez, Jonathan; Rivera, Adín Ramírez; Padilla, Nelson & Dujovne, Diego (2022). A deep learning approach to halo merger tree construction. Monthly notices of the Royal Astronomical Society. ISSN 0035-8711. 514(3), p. 3692–3708. doi: 10.1093/mnras/stac1569. Full text in Research Archive
• Albarracin, Juan F. Hernandez & Rivera, Adín Ramírez (2022). Video Reenactment as Inductive Bias for Content-Motion Disentanglement. IEEE Transactions on Image Processing. ISSN 1057-7149. 31, p. 2365–2374. doi: 10.1109/TIP.2022.3153140. Full text in Research Archive Show summary

  Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-dimensional representations that can be identified and used to feed task-specific models. We introduce MTC-VAE, a self-supervised motion-transfer VAE model to disentangle motion and content from videos. Unlike previous work on video content-motion disentanglement, we adopt a chunk-wise modeling approach and take advantage of the motion information contained in spatiotemporal neighborhoods. Our model yields independent per-chunk representations that preserve temporal consistency. Hence, we reconstruct whole videos in a single forward-pass. We extend the ELBO’s log-likelihood term and include a Blind Reenactment Loss as an inductive bias to leverage motion disentanglement, under the assumption that swapping motion features yields reenactment between two videos. We evaluate our model with recently-proposed disentanglement metrics and show that it outperforms a variety of methods for video motion-content disentanglement. Experiments on video reenactment show the effectiveness of our disentanglement in the input space where our model outperforms the baselines in reconstruction quality and motion alignment.

• Saire, Darwin & Rivera, Adín Ramírez (2022). Global and Local Features Through Gaussian Mixture Models on Image Semantic Segmentation. IEEE Access. 10, p. 77323–77336. doi: 10.1109/ACCESS.2022.3192605. Full text in Research Archive
• Saire, Darwin & Rivera, Adín Ramírez (2021). Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task. IEEE Access. 9, p. 80654–80670. doi: 10.1109/ACCESS.2021.3085218. Full text in Research Archive
• Santander, Miguel Rodríguez; Albarracín, Juan Hernández & Rivera, Adín Ramírez (2021). On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study. Expert Systems With Applications. ISSN 0957-4174. 183. doi: 10.1016/j.eswa.2021.114991. Full text in Research Archive
• Khusainova, Albina; Khan, Adil; Rivera, Adín Ramírez & Romanov, Vitaly (2021). Hierarchical Transformer for Multilingual Machine Translation. In Zampieri, Marcos; Nakov, Preslav; Ljubešic, Nikola; Tiedemann, Jörg; Scherrer, Yves & Jauhiainen, Tommi (Ed.), Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial@EACL 2021. Association for Computational Linguistics (ACL). ISSN 9781954085121. p. 12–20. Full text in Research Archive
• Nikolentzos, Giannis; Thomas, Michalis; Rivera, Adín Ramírez & Vazirgiannis, Michalis (2021). Image Classification using Graph-based Representations and Graph Neural Networks. In Benito, Rosa M.; Cherifi, Chantal; Cherifi, Hocine; Moro, Esteban; Rocha, Luis Mateus & Sales-Pardo, Marta (Ed.), Complex Networks & Their Applications IX. COMPLEX NETWORKS 2020 2020. Springer. ISSN 9783030653514. p. 142–153. doi: 10.1007/978-3-030-65351-4_12. Full text in Research Archive
• Rivera, Adín Ramírez; Khan, Adil; Bekkouch, Imad Eddine Ibrahim & Sheikh, Taimoor Shakeel (2020). Anomaly Detection based on Zero- Shot Outlier Synthesis and Hierarchical Feature Distillation. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X. 33(1), p. 281–291. doi: 10.1109/TNNLS.2020.3027667. Full text in Research Archive
• Iqbal, Md Tauhid Bin; Ryu, Byungyong; Rivera, Adín Ramírez; Makhmudkhujaev, Farkhod; Chae, Oksam & Bae, Sung-Ho (2020). Facial Expression Recognition with Active Local Shape Pattern and Learned-Size Block Representations. IEEE Transactions on Affective Computing. 13(3), p. 1322–1336. doi: 10.1109/TAFFC.2020.2995432. Full text in Research Archive
• Quispe, Rodolfo; Ttito, Darwin; Rivera, Adín Ramírez & Pedrini, Helio (2020). Multi-Stream Networks and Ground- Truth Generation for Crowd Counting. International Journal of Electrical and Computer Engineering Systems. ISSN 1847-6996. 11(1). doi: 10.32985/ijeces.11.1.4. Full text in Research Archive
• Ttito, Darwin; Quispe, Rodolfo; Rivera, Adín Ramírez & Pedrini, Helio (2019). Where are the People? A Multi-Stream Convolutional Neural Network for Crowd Counting via Density Map from Complex Images. In Žagar, Drago; Rimac-Drlje, Snježana; Martinović, Goran; Galić, Irena; Vranješ, Denis & Habijan, Marija (Ed.), IWSSIP 2019, 25th International Conference on Systems, Signals and image processing; 5 - 7 June 2019, Osijek, Croatia. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728132273. doi: 10.1109/IWSSIP.2019.8787217. Full text in Research Archive
• Kim, Byeongwoo; Rivera, Adín Ramírez; Chae, Oksam & Kim, Jaemyun (2019). Background Modeling through Spatiotemporal Edge Feature and Color. In Bebis, George; Boyle, Richard; Parvin, Bahram; Koracin, Darko; Ushizima, Daniela; Chai, Sek; Sueda, Shinjiro; Lin, Xin; Lu, Aidong; Thalmann, Daniel; Wang, Chaoli & Xu, Panpan (Ed.), Advances in Visual Computing. ISVC 2019.. Springer. ISSN 9783030337230. p. 196–208. doi: 10.1007/978-3-030-33723-0_16. Full text in Research Archive
• Zhdanov, Pavel; Khan, Adil; Rivera, Adín Ramírez & Khattak, Asad Masood (2018). Improving Human Action Recognition through Hierarchical Neural Network Classifiers. In Ludermir, Teresa; Braga, Antônio; Roy, Asim; Cavalcanti, George; Príncipe, José Carlos & Lorena, Ana (Ed.), Proceedings of the International Joint Conference on Neural Networks (IJCNN). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781509060146. doi: 10.1109/IJCNN.2018.8489663. Full text in Research Archive
• Kim, Jaemyun; Rivera, Adín Ramírez; Kim, Byeongwoo; Roy, Kaushik & Chae, Oksam (2017). Background Modeling using Adaptive Properties of Hybrid Features. In Distante, Cosimo & Davis, Larry S. (Ed.), Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE Signal Processing Society. ISSN 9781538629390. doi: 10.1109/AVSS.2017.8078475. Full text in Research Archive
• Gusarev, Maxim; Kuleev, Ramil; Khan, Adil; Rivera, Adín Ramírez & Khattak, Asad Masood (2017). Deep Learning Models for Bone Suppression in Chest Radiographs. In Allmendinger, Richard; Corns, Steven; Ashlock, Wendy & Houghten, Sheridan (Ed.), Proceedings of the 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467389884. doi: 10.1109/CIBCB.2017.8058543. Full text in Research Archive
• Dobrenkii, Anton; Kuleev, Ramil; Khan, Adil; Rivera, Adín Ramírez & Khattak, Asad Masood (2017). Large Residual Multiple View 3D CNN for False Positive Reduction in Pulmonary Nodule Detection. In Allmendinger, Richard; Corns, Steven; Ashlock, Wendy & Houghten, Sheridan (Ed.), Proceedings of the 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467389884. doi: 10.1109/CIBCB.2017.8058549. Full text in Research Archive
• Arias, Jhosimar & Rivera, Adín Ramírez (2017). Learning to Cluster with Auxiliary Tasks: A Semi-Supervised Approach. In Torchelsen, Rafael P.; Panozzo, Daniele; Nascimento, Erickson R. & Liu, Zicheng (Ed.), 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781538622193. p. 141–148. doi: 10.1109/SIBGRAPI.2017.25. Full text in Research Archive
• Ryu, Byungyong; Rivera, Adín Ramírez; Kim, Jaemyun & Chae, Oksam (2017). Local Directional Ternary Pattern for Facial Expression Recognition. IEEE Transactions on Image Processing. ISSN 1057-7149. 26(12), p. 6006–6018. doi: 10.1109/TIP.2017.2726010. Full text in Research Archive
• Hong, Seokjin; Kim, Jaemyun; Rivera, Adín Ramírez; Song, Gihun & Chae, Oksam (2016). Edge Shape Pattern for Background Modeling based on Hybrid Local Codes. In Boult, Terry & Nevatia, Ram (Ed.), Proceedings of the 2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE Signal Processing Society. ISSN 9781509038114. doi: 10.1109/AVSS.2016.7738015. Full text in Research Archive
• Kim, Jaemyun; Rivera, Adín Ramírez; Ryu, Byungyong & Chae, Oksam (2015). Simultaneous foreground detection and classification with hybrid features. In Bajcsy, Ruzena; Hager, Greg & Ma, Yi (Ed.), Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467383912. doi: 10.1109/ICCV.2015.378. Full text in Research Archive
• Rivera, Adín Ramírez; Castillo, Jorge Rojas & Chae, Oksam (2015). Local Directional Texture Pattern Image Descriptor. Pattern Recognition Letters. ISSN 0167-8655. 51, p. 94–100. doi: 10.1016/j.patrec.2014.08.012. Full text in Research Archive
• Rivera, Adín Ramírez & Chae, Oksam (2015). Spatiotemporal Directional Number Transitional Graph for Dynamic Texture Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 37(10), p. 2146–2152. doi: 10.1109/TPAMI.2015.2392774. Full text in Research Archive
• Kim, Jaemyun; Rivera, Adín Ramírez; Ryu, Byungyong; Ahn, Kiok & Chae, Oksam (2014). Unattended object detection based on edge-segment distributions. In Ko, Hanseok & Choi, Jin Young (Ed.), Proceedings of the 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781479948710. p. 283–288. doi: 10.1109/AVSS.2014.6918682. Full text in Research Archive
• Kim, Jaemyun; Rivera, Adín Ramírez; Song, Gihun; Ryu, Byungyong & Chae, Oksam (2013). Edge-segment-based Background Modeling: Non-parametric online background update, 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2013, Krakow, 27-30 Aug. 2013. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781479907038. p. 214–219. doi: 10.1109/AVSS.2013.6636642. Full text in Research Archive
• Rivera, Adín Ramírez; Castillo, Jorge Rojas & Chae, Oksam (2013). Local Directional Number Pattern for Face Analysis: Face and Expression Recognition. IEEE Transactions on Image Processing. ISSN 1057-7149. 22(5), p. 1740–1752. doi: 10.1109/TIP.2012.2235848. Full text in Research Archive
• Kim, Jaemyun; Murshed, Mahbub; Rivera, Adín Ramírez & Chae, Oksam (2013). Background Modelling Using Edge-Segment Distributions. International Journal of Advanced Robotic Systems (IJARS). ISSN 1729-8806. 10. doi: 10.5772/54185. Full text in Research Archive
• Rivera, Adín Ramírez; Murshed, Mahbub; Kim, Jaemyun & Chae, Oksam (2013). Background Modeling Through Statistical Edge-Segment Distributions. IEEE transactions on circuits and systems for video technology (Print). ISSN 1051-8215. 23(8), p. 1375–1387. doi: 10.1109/TCSVT.2013.2242551. Full text in Research Archive
• Rivera, Adín Ramírez; Castillo, Jorge Rojas & Chae, Oksam (2012). Local Gaussian Directional Pattern for Face Recognition. In Saito, Hideo & Aoki, Yoshimitsu (Ed.), Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012); November 11-15, 2012; Tsukuba, Japan. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9784990644109. p. 1000–1003. Full text in Research Archive
• Castillo, Jorge Rojas; Rivera, Adín Ramírez & Chae, Oksam (2012). Facial Expression Recognition Based on Local Sign Directional Pattern. In Saber, Eli (Eds.), Proceedings of the 2012 19th IEEE International Conference on Image Processing. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467325332. p. 2613–2616. doi: 10.1109/ICIP.2012.6467434. Full text in Research Archive
• Rivera, Adín Ramírez; Castillo, Jorge Rojas & Chae, Oksam (2012). Recognition of face expressions using Local Principal Texture Pattern. In Saber, Eli (Eds.), Proceedings of the 2012 19th IEEE International Conference on Image Processing. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467325332. p. 2609–2612. doi: 10.1109/ICIP.2012.6467433. Full text in Research Archive
• Rivera, Adín Ramírez; Ryu, Byungyong & Chae, Oksam (2012). Content-Aware Dark Image Enhancement through Channel Division. IEEE Transactions on Image Processing. ISSN 1057-7149. 21(9), p. 3967–3980. doi: 10.1109/TIP.2012.2198667. Full text in Research Archive
• Castillo, Jorge Rojas; Rivera, Adín Ramírez & Chae, Oksam (2012). Robust Facial Recognition Based on Local Gaussian Structural Pattern. International Journal of Innovative Computing, Information and Control. ISSN 1349-4198. 8(12), p. 8399–8413. Full text in Research Archive
• Murshed, Mahbub; Rivera, Adín Ramírez; Kim, Jaemyun & Chae, Oksam (2012). Statistical Binary Edge Frequency Accumulation Model for Moving Object Detection. International Journal of Innovative Computing, Information and Control. ISSN 1349-4198. 8(7(B)), p. 4943–4957. Full text in Research Archive
• Rivera, Adín Ramírez; Murshed, Mahbub & Chae, Oksam (2011). Object Detection through Edge Behavior Modeling. In Foresti, Gian Luca & Rinner, Bernhard (Ed.), Proceedings of the 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781457708459. p. 273–278. doi: 10.1109/AVSS.2011.6027336. Full text in Research Archive
• Murshed, Mahbub; Rivera, Adín Ramírez & Chae, Oksam (2011). Moving Edge Segment Matching for the Detection of Moving Object. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 6753, p. 274–283. doi: 10.1007/978-3-642-21593-3_28. Full text in Research Archive
• Murshed, Mahbub; Rivera, Adín Ramírez & Chae, Oksam (2010). Statistical Background Modeling: An Edge Segment based Moving Object Detection Approach. In Porikli, Fatih (Eds.), Proceedings of the 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781424483112. p. 300–306. doi: 10.1109/AVSS.2010.18. Full text in Research Archive

View all works in NVA

• Choi, Changkyu; Tan, Martine Hjelkrem; Aasan, Marius & Rivera, Adín Ramírez (2026). AI in Our Daily Lives - Panel Discussion. Full text in Research Archive Show summary

  AURoRA researchers co-hosted a public seminar and panel discussion with the Embassy of the Republic of Korea to Norway, held at Litteraturhuset in Oslo as part of the K-Initiative campaign. The evening opened with the talk "Mirrors of Intelligence" by Adín Ramírez Rivera (University of Oslo). The panel then discussed trust, fairness and the societal impact of AI with the audience.

• Rivera, Adín Ramírez & Choi, Changkyu (2026). Mirrors of Intelligence. Full text in Research Archive Show summary

  The lecture focuses on how AI systems are built, what they reflect from human data, and why their outputs require critical judgment. In addition, it explains the development of LLMs and VLMs through large-scale data collection, pre-training, fine-tuning, and human-feedback-based alignment. It highlights both the strengths of AI, such as summarizing well-established knowledge and generating standard code, and its limitations, including biases, hallucinations, and sycophancy. The main takeaway is to use AI as an augmentative tool rather than a replacement for human judgment, while remaining aware of bias, questioning plausible but false information, and developing AI literacy as an essential skill.

• Rivera, Adín Ramírez (2025). Multimodal Intelligence. Full text in Research Archive
• Silva, Thalles; Pedrini, Helio & Rivera, Adín Ramírez (2024). Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features. Full text in Research Archive
• Rivera, Adín Ramírez (2024). Diffusion Models (a tutorial). Full text in Research Archive
• Rivera, Adín Ramírez (2024). Learning representations from high-level structures. Full text in Research Archive Show summary

  This presentation will discuss new breakthroughs in self-supervised representation learning that depart from traditional instance-based contrastive learning. Current methods in self-supervised learning heavily rely on contrasting samples, but this approach presents challenges when augmentations are not feasible within the domain, alter the problem, or when effective data augmentation strategies are unclear. To address these issues, this talk introduces the concept of high-level supervisory signals and advocates for supervised learning of higher-order structures. The speaker will also touch briefly on their research agenda and current topics to link them with Integreat, but the main focus will be on the novel results in self-supervised representation learning.

• Aasan, Marius; Kolbjørnsen, Odd; Solberg, Anne H Schistad & Rivera, Adín Ramírez (2024). A Spitting Image: Modular Superpixel Tokenization in Vision Transformers. Full text in Research Archive
• Aasan, Marius; Kolbjørnsen, Odd; Solberg, Anne H Schistad & Rivera, Adín Ramírez (2024). A Spitting Image: Modular Tokenization in Vision Transformers. Full text in Research Archive
• Rivera, Adín Ramírez; Thomas, Sarina & Choi, Changkyu (2024). Unsupervised Learning of visual feature hierarchy by contrasting hierarchical topic assignments. Full text in Research Archive
• Choi, Changkyu; Thomas, Sarina & Rivera, Adín Ramírez (2024). Unsupervised learning of visual feature hierarchy by contrasting hierarchical topic assignments. Full text in Research Archive
• Aasan, Marius; Kolbjørnsen, Odd; Solberg, Anne H Schistad & Rivera, Adín Ramírez (2024). A Spitting Image: Modular Superpixel Tokenization in Vision Transformers. Full text in Research Archive
• Rivera, Adín Ramírez (2023). Self-Supervised Learning through Clustering. Full text in Research Archive
• Rivera, Adín Ramírez (2023). Transformers: A tutorial. Full text in Research Archive
• Thalles, Silva & Rivera, Adín Ramírez (2023). Representation Learning via Consistent Assignment of Views over Random Partitions. Full text in Research Archive
• Souza, Bruno Cesar de Oliveira; Aasan, Marius; Pedrini, Helio & Rivera, Adín Ramírez (2023). SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering. Full text in Research Archive
• Kenfack, Patrik; Rivera, Adín Ramírez; Khan, Adil & Mazzara, Manuel (2023). Learning Fair Representations through Uniformly Distributed Sensitive Attributes. Full text in Research Archive
• Sinii, Viacheslav; Rivera, Adín Ramírez & Khan, Adil (2023). Understanding the Effectiveness of Cross-Domain Contrastive Unsupervised Domain Adaptation. Full text in Research Archive
• Sabbagh, Kamil; Kenfack, Patrik Joslin; Rivera, Adín Ramírez & Khan, Adil (2023). RepFair-GAN: Mitigating Representation Bias in GANs Using Gradient Clipping. Full text in Research Archive
• Silva, Thalles; Pedrini, Helio & Rivera, Adín Ramírez (2023). Self-supervised Learning of Contextualized Local Visual Embeddings. Full text in Research Archive
• Souza, Bruno Cesar de Oliveira; Aasan, Marius; Pedrini, Helio & Rivera, Adín Ramírez (2023). SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering. Full text in Research Archive
• Tan, Martine Hjelkrem; Rivera, Adín Ramírez & Thomas, Sarina (2023). Hierarchical topic discovery in images; probabilistic modelling of visual data. Full text in Research Archive
• Aasan, Marius; Rivera, Adín Ramírez; Kolbjørnsen, Odd & Solberg, Anne H Schistad (2022). An Information Metric for Partitions on Images using Lattice Theoretic Entropy. Full text in Research Archive
• Silva, Thalles & Rivera, Adín Ramírez (2021). Consistent Assignment for Representation Learning. Full text in Research Archive
• Silva, Matteus; Bittencourt, Luiz Fernando & Rivera, Adín Ramírez (2020). Towards Federated Learning in Edge Com- puting for Real-Time Traffic Estimation in Smart Cities. Full text in Research Archive
• Robles, Sandra; Gómez, Jonathan; Rivera, Adín Ramírez; Gonzáles, Jenny; Padilla, Nelson & Dujovne, Diego (2019). A Halo Merger Tree Generation and Evaluation Framework. Full text in Research Archive
• Saire, Darwin & Rivera, Adín Ramírez (2019). Graph Learning Network: A Structure Learning Algorithm. Full text in Research Archive
• Khusainova, Albina; Khan, Adil & Rivera, Adín Ramírez (2019). SART—Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluation. Full text in Research Archive
• Arias, Jhosimar & Rivera, Adín Ramírez (2017). Is Simple Better?: Revisiting Simple Generative Models for Unsupervised Clustering. Full text in Research Archive
• Kim, Jaemyun; Rivera, Adín Ramírez; Park, Minsun & Chae, Oksam (2012). Scene Modeling using Edge Segment Distributions. Full text in Research Archive

View all works in NVA