{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","cited_by_count":224},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2004.07514","title":"Local-Global Video-Text Interactions for Temporal Grounding","created":"2020-04-16","cited_by_count":188},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"1904.02755","title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions","created":"2019-04-04","cited_by_count":82},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51},{"id":"2011.10132","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","created":"2020-11-19","cited_by_count":50},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50},{"id":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44},{"id":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","cited_by_count":42},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36},{"id":"2109.06400","title":"Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding","created":"2021-09-14","cited_by_count":31},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31},{"id":"2110.05717","title":"Relation-aware Video Reading Comprehension for Temporal Language Grounding","created":"2021-10-12","cited_by_count":27},{"id":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24},{"id":"2303.08345","title":"Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos","created":"2023-03-15","cited_by_count":23},{"id":"2307.14277","title":"G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory","created":"2023-07-26","cited_by_count":21},{"id":"2301.00514","title":"Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding","created":"2023-01-02","cited_by_count":19},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17},{"id":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","cited_by_count":15},{"id":"2411.17473","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","created":"2024-11-26","cited_by_count":15},{"id":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11},{"id":"2509.12145","title":"Open-ended Hierarchical Streaming Video Understanding with Vision Language Models","created":"2025-09-15","cited_by_count":6},{"id":"2505.16376","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","created":"2025-05-22","cited_by_count":5},{"id":"2312.07435","title":"Cross-modal Contrastive Learning with Asymmetric Co-attention Network for Video Moment Retrieval","created":"2023-12-12","cited_by_count":4},{"id":"2508.19242","title":"Autoregressive Universal Video Segmentation Model","created":"2025-08-26","cited_by_count":1}],"next_cursor":null}