{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"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":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"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":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"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":"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":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166},{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106},{"id":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","cited_by_count":86},{"id":"2405.13382","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","created":"2024-05-22","cited_by_count":85},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83},{"id":"1904.02755","title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions","created":"2019-04-04","cited_by_count":82},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2411.18211","title":"TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability","created":"2024-11-27","cited_by_count":70},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66},{"id":"2011.10132","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","created":"2020-11-19","cited_by_count":50},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36},{"id":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31},{"id":"2312.00083","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","created":"2023-11-30","cited_by_count":29},{"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":"2506.18883","title":"Universal Video Temporal Grounding with Generative Multi-modal Large Language Models","created":"2025-06-23","cited_by_count":27},{"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":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","cited_by_count":21},{"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":"2510.17023","title":"Enrich and Detect: Video Temporal Grounding with Multimodal LLMs","created":"2025-10-19","cited_by_count":12},{"id":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11},{"id":"2505.16376","title":"DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos","created":"2025-05-22","cited_by_count":5},{"id":"2510.23043","title":"HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling","created":"2025-10-27","cited_by_count":1}],"next_cursor":null}