{"list":"other","total":84,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"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":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"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":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"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":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"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":"2108.06852","title":"A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction","created":"2021-08-16","cited_by_count":129},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"1809.06181","title":"Dual Encoding for Zero-Example Video Retrieval","created":"2018-09-17","cited_by_count":85},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"2501.06994","title":"Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning","created":"2025-01-13","cited_by_count":59},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52},{"id":"2205.14895","title":"From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering","created":"2022-05-30","cited_by_count":51},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46},{"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":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40},{"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":"2309.14356","title":"COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs","created":"2023-09-23","cited_by_count":39},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35},{"id":"2402.13254","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","created":"2024-02-20","cited_by_count":35},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31},{"id":"1512.00795","title":"Actions ~ Transformations","created":"2015-12-02","cited_by_count":30},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30},{"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":"1702.02738","title":"Joint Discovery of Object States and Manipulation Actions","created":"2017-02-09","cited_by_count":28},{"id":"2206.02928","title":"Neuro-Symbolic Procedural Planning with Commonsense Prompting","created":"2022-06-06","cited_by_count":28},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","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":"2308.08885","title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","created":"2023-08-17","cited_by_count":21},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19},{"id":"2204.03017","title":"Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency","created":"2022-04-06","cited_by_count":15},{"id":"2403.02782","title":"Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos","created":"2024-03-05","cited_by_count":15},{"id":"2310.00608","title":"Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning","created":"2023-10-01","cited_by_count":14},{"id":"1806.10348","title":"Learning Visually-Grounded Semantics from Contrastive Adversarial Samples","created":"2018-06-27","cited_by_count":13},{"id":"2309.14339","title":"Chop & Learn: Recognizing and Generating Object-State Compositions","created":"2023-09-25","cited_by_count":13},{"id":"2311.03550","title":"United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos","created":"2023-11-06","cited_by_count":13},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12},{"id":"2312.01659","title":"RiskBench: A Scenario-based Benchmark for Risk Identification","created":"2023-12-04","cited_by_count":12},{"id":"2211.13500","title":"Multi-Task Learning of Object State Changes from Uncurated Videos","created":"2022-11-24","cited_by_count":10},{"id":"2404.06570","title":"MORPHeus: a Multimodal One-armed Robot-assisted Peeling System with Human Users In-the-loop","created":"2024-04-09","cited_by_count":10},{"id":"2402.18796","title":"MOSAIC: Modular Foundation Models for Assistive and Interactive Cooking","created":"2024-02-29","cited_by_count":9},{"id":"2403.04067","title":"Feel the Bite: Robot-Assisted Inside-Mouth Bite Transfer using Robust Mouth Perception and Physical Interaction-Aware Control","created":"2024-03-06","cited_by_count":9},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6},{"id":"2405.06908","title":"To Ask or Not To Ask: Human-in-the-loop Contextual Bandits with Applications in Robot-Assisted Feeding","created":"2024-05-11","cited_by_count":3},{"id":"2503.18553","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","created":"2025-03-24","cited_by_count":2}],"next_cursor":null}