{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50},{"id":"2310.17323","title":"IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting","created":"2023-10-26","cited_by_count":48},{"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":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46},{"id":"2011.03920","title":"Integrating Human Gaze into Attention for Egocentric Activity Recognition","created":"2020-11-08","cited_by_count":42},{"id":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39},{"id":"2403.16428","title":"Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects","created":"2024-03-25","cited_by_count":35},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31},{"id":"2305.07214","title":"MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition","created":"2023-05-12","cited_by_count":26},{"id":"2306.08713","title":"What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations","created":"2023-06-14","cited_by_count":25},{"id":"2308.11489","title":"Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition","created":"2023-08-22","cited_by_count":20},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20},{"id":"2407.06628","title":"Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition","created":"2024-07-09","cited_by_count":18},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17},{"id":"2312.02638","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","created":"2023-12-05","cited_by_count":17},{"id":"2505.23694","title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers","created":"2025-05-29","cited_by_count":17},{"id":"2406.08379","title":"Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities","created":"2024-06-12","cited_by_count":15},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11},{"id":"2408.06437","title":"HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization","created":"2024-08-12","cited_by_count":10},{"id":"1802.10250","title":"Joint Event Detection and Description in Continuous Video Streams","created":"2018-02-28","cited_by_count":9},{"id":"2109.02955","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","created":"2021-09-07","cited_by_count":9},{"id":"2408.00759","title":"Text-Guided Video Masked Autoencoder","created":"2024-08-01","cited_by_count":8},{"id":"2504.02397","title":"Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval","created":"2025-04-03","cited_by_count":8},{"id":"2403.19811","title":"X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization","created":"2024-03-28","cited_by_count":6},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5},{"id":"2504.03948","title":"ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition","created":"2025-04-04","cited_by_count":3}],"next_cursor":null}