{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"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":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"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":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"1905.05143","title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","created":"2019-05-13","cited_by_count":57},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53},{"id":"2205.02300","title":"P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision","created":"2022-05-04","cited_by_count":52},{"id":"2109.04869","title":"PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks","created":"2021-09-10","cited_by_count":45},{"id":"1812.02501","title":"Zero-Shot Anticipation for Instructional Activities","created":"2018-12-06","cited_by_count":43},{"id":"1912.07148","title":"Predicting the Future: A Jointly Learnt Model for Action Anticipation","created":"2019-12-16","cited_by_count":41},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","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":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29},{"id":"2206.02928","title":"Neuro-Symbolic Procedural Planning with Commonsense Prompting","created":"2022-06-06","cited_by_count":28},{"id":"1904.04231","title":"Relational Action Forecasting","created":"2019-04-08","cited_by_count":27},{"id":"2303.13519","title":"Learning and Verification of Task Structure in Instructional Videos","created":"2023-03-23","cited_by_count":26},{"id":"2011.02751","title":"Goal-driven Long-Term Trajectory Prediction","created":"2020-11-05","cited_by_count":24},{"id":"2004.07711","title":"Knowledge Distillation for Action Anticipation via Label Smoothing","created":"2020-04-16","cited_by_count":21},{"id":"1909.09278","title":"Forecasting Future Action Sequences with Neural Memory Networks","created":"2019-09-20","cited_by_count":18},{"id":"2207.00579","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","created":"2022-07-01","cited_by_count":18},{"id":"2306.16545","title":"Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023","created":"2023-06-28","cited_by_count":16},{"id":"2209.05044","title":"Predicting the Next Action by Modeling the Abstract Goal","created":"2022-09-12","cited_by_count":14},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13},{"id":"2307.01467","title":"Technical Report for Ego4D Long Term Action Anticipation Challenge 2023","created":"2023-07-04","cited_by_count":7},{"id":"2210.05991","title":"Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation","created":"2022-10-12","cited_by_count":6},{"id":"2209.15501","title":"A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos","created":"2022-09-30","cited_by_count":4}],"next_cursor":null}