{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"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":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"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":"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":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66},{"id":"2101.10511","title":"Generic Event Boundary Detection: A Benchmark for Event Segmentation","created":"2021-01-26","cited_by_count":65},{"id":"2403.04593","title":"Embodied Understanding of Driving Scenarios","created":"2024-03-07","cited_by_count":63},{"id":"2011.10132","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","created":"2020-11-19","cited_by_count":50},{"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":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","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":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34},{"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":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31},{"id":"2103.16848","title":"Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding","created":"2021-03-31","cited_by_count":29},{"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":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","cited_by_count":28},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28},{"id":"2109.10678","title":"Natural Language Video Localization with Learnable Moment Proposals","created":"2021-09-22","cited_by_count":27},{"id":"2110.05717","title":"Relation-aware Video Reading Comprehension for Temporal Language Grounding","created":"2021-10-12","cited_by_count":27},{"id":"2302.13372","title":"Localizing Moments in Long Video Via Multimodal Guidance","created":"2023-02-26","cited_by_count":23},{"id":"2105.08481","title":"Parallel Attention Network with Sequence Matching for Video Grounding","created":"2021-05-18","cited_by_count":22},{"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":"2112.04771","title":"Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection","created":"2021-12-09","cited_by_count":20},{"id":"2301.00514","title":"Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding","created":"2023-01-02","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":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","cited_by_count":15},{"id":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","cited_by_count":12},{"id":"2205.07134","title":"ETAD: Training Action Detection End to End on a Laptop","created":"2022-05-14","cited_by_count":10},{"id":"2111.15050","title":"AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant","created":"2021-11-30","cited_by_count":8},{"id":"2407.12622","title":"Rethinking the Architecture Design for Efficient Generic Event Boundary Detection","created":"2024-07-17","cited_by_count":7}],"next_cursor":null}