{"list":"other","total":85,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"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":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"1803.07640","title":"AllenNLP: A Deep Semantic Natural Language Processing Platform","created":"2018-03-20","cited_by_count":347},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"1810.09305","title":"WikiHow: A Large Scale Text Summarization Dataset","created":"2018-10-18","cited_by_count":204},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"1912.11850","title":"Graph Embedded Pose Clustering for Anomaly Detection","created":"2019-12-26","cited_by_count":95},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"1605.04988","title":"Going Deeper into Action Recognition: A Survey","created":"2016-05-16","cited_by_count":55},{"id":"1909.13155","title":"Weakly Supervised Energy-Based Learning for Action Segmentation","created":"2019-09-28","cited_by_count":53},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51},{"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":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","cited_by_count":42},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40},{"id":"2108.11996","title":"Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers","created":"2021-08-26","cited_by_count":39},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39},{"id":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39},{"id":"2304.13265","title":"StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos","created":"2023-04-26","cited_by_count":37},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36},{"id":"1512.00795","title":"Actions ~ Transformations","created":"2015-12-02","cited_by_count":30},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28},{"id":"2303.13519","title":"Learning and Verification of Task Structure in Instructional Videos","created":"2023-03-23","cited_by_count":26},{"id":"2406.01486","title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","created":"2024-06-03","cited_by_count":26},{"id":"2403.01599","title":"SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos","created":"2024-03-03","cited_by_count":24},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23},{"id":"2303.15167","title":"Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features","created":"2023-03-27","cited_by_count":21},{"id":"2406.15395","title":"An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction","created":"2024-04-29","cited_by_count":19},{"id":"2307.05721","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","created":"2023-07-09","cited_by_count":18},{"id":"2307.16453","title":"Every Mistake Counts in Assembly","created":"2023-07-31","cited_by_count":18},{"id":"2405.19387","title":"Video Anomaly Detection in 10 Years: A Survey and Outlook","created":"2024-05-29","cited_by_count":18},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","cited_by_count":17},{"id":"1701.07851","title":"Human-Robot Mutual Adaptation in Shared Autonomy","created":"2017-01-26","cited_by_count":16},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16},{"id":"2403.11021","title":"Towards Neuro-Symbolic Video Understanding","created":"2024-03-16","cited_by_count":16},{"id":"2311.01851","title":"Holistic Representation Learning for Multitask Trajectory Anomaly Detection","created":"2023-11-03","cited_by_count":15},{"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":"2011.13160","title":"Transformation Driven Visual Reasoning","created":"2020-11-26","cited_by_count":14},{"id":"2304.08210","title":"ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding","created":"2023-04-17","cited_by_count":14},{"id":"2409.17027","title":"Counterfactual Token Generation in Large Language Models","created":"2024-09-25","cited_by_count":14},{"id":"2309.14339","title":"Chop & Learn: Recognizing and Generating Object-State Compositions","created":"2023-09-25","cited_by_count":13},{"id":"2311.15619","title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","created":"2023-11-27","cited_by_count":12},{"id":"2503.22405","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","created":"2025-03-28","cited_by_count":12},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10},{"id":"2411.02570","title":"TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric Videos","created":"2024-11-04","cited_by_count":10},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8},{"id":"2412.01987","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","created":"2024-12-02","cited_by_count":8},{"id":"2411.15106","title":"About Time: Advances, Challenges, and Outlooks of Action Understanding","created":"2024-11-22","cited_by_count":6},{"id":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5},{"id":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5},{"id":"2410.10497","title":"Continual Learning Improves Zero-Shot Action Recognition","created":"2024-10-14","cited_by_count":5},{"id":"2510.12385","title":"Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling","created":"2025-10-14","cited_by_count":3},{"id":"2411.05474","title":"Enhancing Robustness in Language-Driven Robotics: A Modular Approach to Failure Reduction","created":"2024-11-08","cited_by_count":2}],"next_cursor":null}