{"total":68,"rows":[{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2307.13565","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","created":"2023-07-25","cited_by_count":130,"area":null},{"id":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104,"area":null},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59,"area":null},{"id":"2204.12454","title":"Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images","created":"2022-04-26","cited_by_count":43,"area":null},{"id":"2105.14039","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","created":"2021-05-28","cited_by_count":40,"area":null},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38,"area":null},{"id":"2212.05463","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","created":"2022-12-11","cited_by_count":35,"area":null},{"id":"2406.09196","title":"Adaptive Slot Attention: Object Discovery with Dynamic Slot Number","created":"2024-06-13","cited_by_count":34,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2203.09630","title":"Monotonic Differentiable Sorting Networks","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25,"area":null},{"id":"2312.15010","title":"SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology","created":"2023-12-22","cited_by_count":25,"area":null},{"id":"2202.07570","title":"ScoreNet: Learning Non-Uniform Attention and Augmentation for Transformer-Based Histopathological Image Classification","created":"2022-02-15","cited_by_count":21,"area":null},{"id":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2106.02694","title":"Efficient Classification of Very Large Images with Tiny Objects","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2210.13007","title":"Iterative Patch Selection for High-Resolution Image Recognition","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2305.16358","title":"Differentiable Clustering with Perturbed Spanning Forests","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2502.12370","title":"Positional Encoding in Transformer-Based Time Series Models: A Survey","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2301.02009","title":"Learning by Sorting: Self-supervised Learning with Group Ordering Constraints","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2111.07534","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2210.04615","title":"EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification","created":"2022-10-07","cited_by_count":12,"area":null},{"id":"2204.00656","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","created":"2022-04-01","cited_by_count":11,"area":null},{"id":"2203.14215","title":"Knowledge Mining with Scene Text for Fine-Grained Recognition","created":"2022-03-27","cited_by_count":10,"area":null},{"id":"2207.09759","title":"Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8,"area":"lr"},{"id":"2501.02922","title":"Label-free Concept Based Multiple Instance Learning for Gigapixel Histopathology","created":"2025-01-06","cited_by_count":8,"area":null},{"id":"2110.15072","title":"Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2305.06114","title":"Few-shot Action Recognition via Intra- and Inter-Video Information Maximization","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2411.18225","title":"PATHS: A Hierarchical Transformer for Efficient Whole Slide Image Analysis","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2211.10420","title":"Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2404.00680","title":"Learning to Rank Patches for Unbiased Image Redundancy Reduction","created":"2024-03-31","cited_by_count":6,"area":null},{"id":"2210.08159","title":"Dynamics-aware Adversarial Attack of Adaptive Neural Networks","created":"2022-10-15","cited_by_count":5,"area":null},{"id":"2501.10814","title":"No More Sliding Window: Efficient 3D Medical Image Segmentation with Differentiable Top-k Patch Sampling","created":"2025-01-18","cited_by_count":5,"area":null},{"id":"2505.18051","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2303.06522","title":"Token Sparsification for Faster Medical Image Segmentation","created":"2023-03-11","cited_by_count":4,"area":"inference"},{"id":"2504.02227","title":"VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2411.00119","title":"Soft Condorcet Optimization for Ranking of General Agents","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2110.04954","title":"Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2203.12873","title":"Weakly-Supervised End-to-End CAD Retrieval to Scan Objects","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2203.14154","title":"NUNet: Deep Learning for Non-Uniform Super-Resolution of Turbulent Flows","created":"2022-03-26","cited_by_count":2,"area":null},{"id":"2301.13817","title":"Patch Gradient Descent: Training Neural Networks on Very Large Images","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2304.00961","title":"Self-Ordering Point Clouds","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2307.02245","title":"Set Learning for Accurate and Calibrated Models","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2401.04403","title":"MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2502.16627","title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.05491","title":"REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2201.01415","title":"Problem-dependent attention and effort in neural networks with applications to image resolution and model selection","created":"2022-01-05","cited_by_count":1,"area":null},{"id":"2301.05213","title":"Learning to Summarize Videos by Contrasting Clips","created":"2023-01-12","cited_by_count":1,"area":null},{"id":"2408.15829","title":"SITransformer: Shared Information-Guided Transformer for Extreme Multimodal Summarization","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2503.05622","title":"Decision-aware training of spatiotemporal forecasting models to select a top K subset of sites for intervention","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2509.14640","title":"DyWPE: Signal-Aware Dynamic Wavelet Positional Encoding for Time Series Transformers","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2511.07560","title":"EvoPS: Evolutionary Patch Selection for Whole Slide Image Analysis in Computational Pathology","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2606.03148","title":"$A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2107.03742","title":"Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2204.13492","title":"Representation Recycling for Streaming Video Analysis","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2206.03367","title":"Localizing Semantic Patches for Accelerating Image Classification","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2206.12420","title":"SCAI: A Spectral data Classification framework with Adaptive Inference for the IoT platform","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2405.07166","title":"Resource Efficient Perception for Vision Systems","created":"2024-05-12","cited_by_count":0,"area":null},{"id":"2412.11237","title":"On the Generalizability of Iterative Patch Selection for Memory-Efficient High-Resolution Image Classification","created":"2024-12-15","cited_by_count":0,"area":null},{"id":"2602.12189","title":"WaveFormer: Wavelet Embedding Transformer for Biomedical Signals","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.02063","title":"ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.05507","title":"Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.07606","title":"TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2609.03085","title":"Solving the Needle-in-a-Haystack Problem in Mammography Vision-Language Model with Differentiable Subset Sampling","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.04698","title":"LookThere! Sparse Vision by Reinforced Selection","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}