{"list":"other","total":70,"rows":[{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"1909.03877","title":"Gaussian Temporal Awareness Networks for Action Localization","created":"2019-09-09","cited_by_count":135},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"2008.09837","title":"Revisiting Anchor Mechanisms for Temporal Action Localization","created":"2020-08-22","cited_by_count":75},{"id":"1807.10706","title":"Diagnosing Error in Temporal Action Detectors","created":"2018-07-27","cited_by_count":71},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61},{"id":"2311.17241","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","created":"2023-11-28","cited_by_count":47},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42},{"id":"2204.02932","title":"An Empirical Study of End-to-End Temporal Action Detection","created":"2022-04-06","cited_by_count":40},{"id":"2503.06169","title":"Treble Counterfactual VLMs: A Causal Approach to Hallucination","created":"2025-03-08","cited_by_count":35},{"id":"2411.08227","title":"DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection","created":"2024-11-12","cited_by_count":29},{"id":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","cited_by_count":28},{"id":"2303.09055","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","created":"2023-03-16","cited_by_count":28},{"id":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22},{"id":"2211.14053","title":"Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization","created":"2022-11-25","cited_by_count":19},{"id":"2303.14863","title":"DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion","created":"2023-03-27","cited_by_count":19},{"id":"2407.03197","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","created":"2024-07-03","cited_by_count":19},{"id":"2503.06166","title":"Secure On-Device Video OOD Detection Without Backpropagation","created":"2025-03-08","cited_by_count":19},{"id":"2206.14989","title":"A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA","created":"2022-06-30","cited_by_count":18},{"id":"2505.14106","title":"A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations","created":"2025-05-20","cited_by_count":17},{"id":"2312.01897","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","created":"2023-12-04","cited_by_count":16},{"id":"2412.07277","title":"Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger","created":"2024-12-10","cited_by_count":12},{"id":"2505.05279","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","created":"2025-05-08","cited_by_count":11},{"id":"2504.14541","title":"Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation","created":"2025-04-20","cited_by_count":10},{"id":"2408.08143","title":"Unlearnable Examples Detection via Iterative Filtering","created":"2024-08-15","cited_by_count":9},{"id":"2507.07483","title":"Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking","created":"2025-07-10","cited_by_count":9},{"id":"2511.07049","title":"From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge","created":"2025-11-10","cited_by_count":9},{"id":"2407.17792","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","created":"2024-07-25","cited_by_count":8},{"id":"2404.10880","title":"HumMUSS: Human Motion Understanding using State Space Models","created":"2024-04-16","cited_by_count":6},{"id":"2411.09126","title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","created":"2024-11-14","cited_by_count":6},{"id":"1611.09053","title":"Bidirectional Multirate Reconstruction for Temporal Modeling in Videos","created":"2016-11-28","cited_by_count":5},{"id":"2502.16602","title":"VidLBEval: Benchmarking and Mitigating Language Bias in Video-Involved LVLMs","created":"2025-02-23","cited_by_count":4},{"id":"2308.03725","title":"Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation","created":"2023-08-07","cited_by_count":3},{"id":"2507.14042","title":"Training-free Token Reduction for Vision Mamba","created":"2025-07-18","cited_by_count":1}],"next_cursor":null}