{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"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":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1912.03590","title":"Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language","created":"2019-12-08","cited_by_count":285},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190},{"id":"2009.08553","title":"Generation-Augmented Retrieval for Open-domain Question Answering","created":"2020-09-17","cited_by_count":186},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","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":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148},{"id":"1812.00087","title":"MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment","created":"2018-11-30","cited_by_count":145},{"id":"1910.14303","title":"Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos","created":"2019-10-31","cited_by_count":135},{"id":"1804.05113","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","created":"2018-04-13","cited_by_count":128},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128},{"id":"2310.16436","title":"DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models","created":"2023-10-25","cited_by_count":128},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98},{"id":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88},{"id":"1811.08925","title":"MAC: Mining Activity Concepts for Language-based Temporal Localization","created":"2018-11-21","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":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79},{"id":"2309.14494","title":"Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator","created":"2023-09-25","cited_by_count":74},{"id":"2401.02309","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","created":"2024-01-04","cited_by_count":59},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46},{"id":"2309.01151","title":"EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment","created":"2023-09-03","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":"2207.13457","title":"Reducing the Vision and Language Bias for Temporal Sentence Grounding","created":"2022-07-27","cited_by_count":35},{"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":"1908.03846","title":"Exploiting Temporal Relationships in Video Moment Localization with Natural Language","created":"2019-08-11","cited_by_count":33},{"id":"2309.01155","title":"LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models","created":"2023-09-03","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":"2309.03473","title":"Temporal Collection and Distribution for Referring Video Object Segmentation","created":"2023-09-07","cited_by_count":27},{"id":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25},{"id":"2404.09263","title":"Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection","created":"2024-04-14","cited_by_count":25},{"id":"2404.11998","title":"Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation","created":"2024-04-18","cited_by_count":23},{"id":"2207.13450","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","created":"2022-07-27","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":"2502.11697","title":"MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow","created":"2025-02-17","cited_by_count":17},{"id":"2111.01673","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","created":"2021-11-02","cited_by_count":15},{"id":"2507.07831","title":"Rethinking Query-based Transformer for Continual Image Segmentation","created":"2025-07-10","cited_by_count":14},{"id":"2407.10084","title":"Part2Object: Hierarchical Unsupervised 3D Instance Segmentation","created":"2024-07-14","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":"2407.10083","title":"Plain-Det: A Plain Multi-Dataset Object Detector","created":"2024-07-14","cited_by_count":9},{"id":"2406.00143","title":"Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding","created":"2024-05-31","cited_by_count":6},{"id":"2201.10168","title":"Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos","created":"2022-01-25","cited_by_count":3}],"next_cursor":null}