{"total":59,"rows":[{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446,"area":"diffusion"},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215,"area":null},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2105.08054","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","created":"2021-05-17","cited_by_count":85,"area":null},{"id":"2103.17263","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","created":"2021-03-31","cited_by_count":81,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50,"area":null},{"id":"2105.05217","title":"Representation Learning via Global Temporal Alignment and Cycle-Consistency","created":"2021-05-11","cited_by_count":44,"area":null},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44,"area":null},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43,"area":null},{"id":"2108.02722","title":"Video Contrastive Learning with Global Context","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2201.08379","title":"Learning Pixel Trajectories with Multiscale Contrastive Random Walks","created":"2022-01-20","cited_by_count":36,"area":null},{"id":"2308.11796","title":"Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations","created":"2023-08-22","cited_by_count":35,"area":null},{"id":"2211.10831","title":"Joint Embedding Predictive Architectures Focus on Slow Features","created":"2022-11-20","cited_by_count":30,"area":"wm"},{"id":"2101.06553","title":"Self-Supervised Representation Learning from Flow Equivariance","created":"2021-01-16","cited_by_count":28,"area":null},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23,"area":null},{"id":"2304.00571","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","created":"2023-04-02","cited_by_count":22,"area":null},{"id":"2104.01286","title":"Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation","created":"2021-04-03","cited_by_count":21,"area":null},{"id":"2210.06433","title":"Self-supervised video pretraining yields robust and more human-aligned visual representations","created":"2022-10-12","cited_by_count":20,"area":null},{"id":"2105.06463","title":"Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency","created":"2021-05-13","cited_by_count":19,"area":null},{"id":"2108.04294","title":"Learning to Cut by Watching Movies","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2109.13499","title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","created":"2021-09-28","cited_by_count":16,"area":null},{"id":"2112.05181","title":"Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision","created":"2021-12-09","cited_by_count":15,"area":null},{"id":"2204.03017","title":"Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency","created":"2022-04-06","cited_by_count":15,"area":null},{"id":"2207.12389","title":"MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation","created":"2022-07-25","cited_by_count":15,"area":null},{"id":"2207.13492","title":"Time to augment self-supervised visual representation learning","created":"2022-07-27","cited_by_count":15,"area":null},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2207.10456","title":"Semantic-Aware Fine-Grained Correspondence","created":"2022-07-21","cited_by_count":13,"area":null},{"id":"2209.07778","title":"Spatial-then-Temporal Self-Supervised Learning for Video Correspondence","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2408.11208","title":"PooDLe: Pooled and dense self-supervised learning from naturalistic videos","created":"2024-08-20","cited_by_count":11,"area":null},{"id":"2203.16632","title":"Controllable Augmentations for Video Representation Learning","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2407.06704","title":"Self-supervised visual learning from interactions with objects","created":"2024-07-09","cited_by_count":10,"area":null},{"id":"2409.16288","title":"Self-Supervised Any-Point Tracking by Contrastive Random Walks","created":"2024-09-24","cited_by_count":10,"area":null},{"id":"2103.12719","title":"Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations","created":"2021-03-23","cited_by_count":8,"area":null},{"id":"2105.05838","title":"Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning","created":"2021-05-12","cited_by_count":6,"area":null},{"id":"2310.00887","title":"GRID: A Platform for General Robot Intelligence Development","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2112.04480","title":"Exploring Temporal Granularity in Self-Supervised Video Representation Learning","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2405.05143","title":"Learning Object Semantic Similarity with Self-Supervision","created":"2024-04-19","cited_by_count":5,"area":null},{"id":"2506.08694","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2111.11433","title":"Towards Tokenized Human Dynamics Representation","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2207.03866","title":"Pixel-level Correspondence for Self-Supervised Learning from Video","created":"2022-07-08","cited_by_count":3,"area":null},{"id":"2210.01379","title":"Extraneousness-Aware Imitation Learning","created":"2022-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2506.03148","title":"Self-Supervised Spatial Correspondence Across Modalities","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2105.09909","title":"PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection","created":"2021-05-06","cited_by_count":2,"area":null},{"id":"2112.00804","title":"PreViTS: Contrastive Pretraining with Video Tracking Supervision","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2312.00277","title":"Text Attribute Control via Closed-Loop Disentanglement","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2510.05558","title":"Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2302.06540","title":"Imitation from Observation With Bootstrapped Contrastive Learning","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2312.11436","title":"Layerwise complexity-matched learning yields an improved model of cortical area V2","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2501.02966","title":"Human Gaze Boosts Object-Centered Representation Learning","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2105.03533","title":"Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2110.07082","title":"The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2512.02339","title":"Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision","created":"2025-12-02","cited_by_count":0,"area":"diffusion"},{"id":"2602.04462","title":"Temporal Slowness in Central Vision Drives Semantic Object Learning","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.13912","title":"Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video","created":"2026-03-14","cited_by_count":0,"area":null}],"next_cursor":null}