{"list":"other","total":60,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"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":"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":"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":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"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":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"1804.07014","title":"To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression","created":"2018-04-19","cited_by_count":157},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"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":"1811.08925","title":"MAC: Mining Activity Concepts for Language-based Temporal Localization","created":"2018-11-21","cited_by_count":84},{"id":"1909.05010","title":"Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction","created":"2019-09-11","cited_by_count":84},{"id":"1904.02755","title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions","created":"2019-04-04","cited_by_count":82},{"id":"1908.07236","title":"Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention","created":"2019-08-20","cited_by_count":81},{"id":"2508.05630","title":"MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes","created":"2025-08-07","cited_by_count":62},{"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":"1611.07675","title":"Video Captioning with Transferred Semantic Attributes","created":"2016-11-23","cited_by_count":46},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"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":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35},{"id":"1908.03846","title":"Exploiting Temporal Relationships in Video Moment Localization with Natural Language","created":"2019-08-11","cited_by_count":33},{"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":"2012.02646","title":"Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2020-12-04","cited_by_count":29},{"id":"2103.16848","title":"Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding","created":"2021-03-31","cited_by_count":29},{"id":"2110.05717","title":"Relation-aware Video Reading Comprehension for Temporal Language Grounding","created":"2021-10-12","cited_by_count":27},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","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":"2303.04995","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","created":"2023-03-09","cited_by_count":18},{"id":"2205.12886","title":"You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos","created":"2022-05-25","cited_by_count":13},{"id":"2312.02232","title":"HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses","created":"2023-12-04","cited_by_count":12},{"id":"2205.05854","title":"Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos","created":"2022-05-12","cited_by_count":10},{"id":"2205.07134","title":"ETAD: Training Action Detection End to End on a Laptop","created":"2022-05-14","cited_by_count":10},{"id":"2504.07519","title":"VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding","created":"2025-04-10","cited_by_count":9},{"id":"2209.00407","title":"MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition","created":"2022-09-01","cited_by_count":8},{"id":"2102.04621","title":"TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition","created":"2021-02-09","cited_by_count":7},{"id":"2512.24097","title":"Factorized Learning for Temporally Grounded Video-Language Models","created":"2025-12-30","cited_by_count":4},{"id":"2311.17428","title":"SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation","created":"2023-11-29","cited_by_count":1}],"next_cursor":null}