{"url":"/task/hard-attention","name":"Hard Attention","slug":"hard-attention","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":100,"papers_with_code":41,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":41,"tagged_in_all":100,"items":[{"url":"/paper/recurrent-models-of-visual-attention","title":"Recurrent Models of Visual Attention","date":"2014-06-24","arxiv_id":"1406.6247","repositories_listed":20,"syntology":{"n":24,"n_ran":7,"n_unverified":17,"n_pointer_only":1}},{"url":"/paper/dual-attention-networks-for-few-shot-fine","title":"Dual Attention Networks for Few-Shot Fine-Grained Recognition","date":"2022-06-28","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/deep-attention-recurrent-q-network","title":"Deep Attention Recurrent Q-Network","date":"2015-12-05","arxiv_id":"1512.01693","repositories_listed":3,"syntology":null},{"url":"/paper/learning-texture-transformer-network-for-1","title":"Learning Texture Transformer Network for Image Super-Resolution","date":"2020-06-07","arxiv_id":"2006.04139","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/190807644","title":"Saccader: Improving Accuracy of Hard Attention Models for Vision","date":"2019-08-20","arxiv_id":"1908.07644","repositories_listed":2,"syntology":null},{"url":"/paper/exact-hard-monotonic-attention-for-character","title":"Exact Hard Monotonic Attention for Character-Level Transduction","date":"2019-05-15","arxiv_id":"1905.06319","repositories_listed":2,"syntology":null},{"url":"/paper/hard-non-monotonic-attention-for-character","title":"Hard Non-Monotonic Attention for Character-Level Transduction","date":"2018-08-29","arxiv_id":"1808.10024","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/overcoming-catastrophic-forgetting-with-hard","title":"Overcoming catastrophic forgetting with hard attention to the task","date":"2018-01-04","arxiv_id":"1801.01423","repositories_listed":2,"syntology":null},{"url":"/paper/center-guided-classifier-for-semantic","title":"Center-guided Classifier for Semantic Segmentation of Remote Sensing Images","date":"2025-03-21","arxiv_id":"2503.16963","repositories_listed":1,"syntology":null},{"url":"/paper/hard-attention-gates-with-gradient-routing","title":"Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing","date":"2024-07-05","arxiv_id":"2407.04400","repositories_listed":1,"syntology":null},{"url":"/paper/trip-trainable-region-of-interest-prediction","title":"TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision","date":"2024-06-25","arxiv_id":"2406.17483","repositories_listed":1,"syntology":null},{"url":"/paper/tree-based-hard-attention-with-self","title":"Recurrent Alignment with Hard Attention for Hierarchical Text Rating","date":"2024-02-14","arxiv_id":"2402.08874","repositories_listed":1,"syntology":null},{"url":"/paper/mutual-distillation-learning-for-person-re","title":"Mutual Distillation Learning For Person Re-Identification","date":"2024-01-12","arxiv_id":"2401.06430","repositories_listed":1,"syntology":null},{"url":"/paper/vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/investigation-of-architectures-and-receptive","title":"Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation","date":"2023-08-18","arxiv_id":"2308.09593","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-learning-dynamics-of-attention","title":"On the Learning Dynamics of Attention Networks","date":"2023-07-25","arxiv_id":"2307.13421","repositories_listed":1,"syntology":null},{"url":"/paper/hat-cl-a-hard-attention-to-the-task-pytorch","title":"HAT-CL: A Hard-Attention-to-the-Task PyTorch Library for Continual Learning","date":"2023-07-18","arxiv_id":"2307.09653","repositories_listed":1,"syntology":null},{"url":"/paper/coherent-concept-based-explanations-in","title":"Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis","date":"2023-04-10","arxiv_id":"2304.04579","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-perceive-in-deep-model-free","title":"Learning to Perceive in Deep Model-Free Reinforcement Learning","date":"2023-01-10","arxiv_id":"2301.03730","repositories_listed":1,"syntology":null},{"url":"/paper/table-retrieval-may-not-necessitate-table","title":"Table Retrieval May Not Necessitate Table-specific Model Design","date":"2022-05-19","arxiv_id":"2205.09843","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/binding-actions-to-objects-in-world-models","title":"Binding Actions to Objects in World Models","date":"2022-04-27","arxiv_id":"2204.13022","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/consistency-driven-sequential-transformers","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","date":"2022-04-01","arxiv_id":"2204.00656","repositories_listed":1,"syntology":null},{"url":"/paper/a-probabilistic-hard-attention-model-for","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","date":"2021-11-15","arxiv_id":"2111.07534","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-interlocking-dynamics-of","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","date":"2021-10-26","arxiv_id":"2110.13880","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/self-attention-networks-can-process-bounded","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","date":"2021-05-24","arxiv_id":"2105.11115","repositories_listed":1,"syntology":null},{"url":"/paper/amr-parsing-with-action-pointer-transformer","title":"AMR Parsing with Action-Pointer Transformer","date":"2021-04-29","arxiv_id":"2104.14674","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fanet-a-feedback-attention-network-for","title":"FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation","date":"2021-03-31","arxiv_id":"2103.17235","repositories_listed":1,"syntology":null},{"url":"/paper/hard-attention-for-scalable-image","title":"Hard-Attention for Scalable Image Classification","date":"2021-02-20","arxiv_id":"2102.10212","repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-attention-mechanism-for-weakly","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","date":"2021-01-03","arxiv_id":"2101.00545","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-transformers-with-approximate-1","title":"AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models","date":"2020-10-07","arxiv_id":"2010.03688","repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}