{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2603.19312","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","created":"2026-03-13","cited_by_count":273},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2511.08544","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","created":"2025-11-11","cited_by_count":254},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141},{"id":"2509.20354","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","created":"2025-09-24","cited_by_count":139},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121},{"id":"2602.10098","title":"VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model","created":"2026-02-10","cited_by_count":118},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"1908.03477","title":"Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings","created":"2019-08-09","cited_by_count":101},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2007.05405","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","created":"2020-07-10","cited_by_count":66},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44},{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42},{"id":"2505.04999","title":"CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations","created":"2025-05-08","cited_by_count":41},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39},{"id":"2410.02746","title":"Contrastive Localized Language-Image Pre-Training","created":"2024-10-03","cited_by_count":33},{"id":"2505.04410","title":"DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception","created":"2025-05-07","cited_by_count":33},{"id":"2506.15691","title":"What Do Latent Action Models Actually Learn?","created":"2025-05-27","cited_by_count":32},{"id":"2306.01669","title":"Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning","created":"2023-06-02","cited_by_count":30},{"id":"2211.16963","title":"Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition","created":"2022-11-30","cited_by_count":27},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25},{"id":"2204.05235","title":"Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets","created":"2022-04-11","cited_by_count":23},{"id":"2307.09548","title":"Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions","created":"2023-07-18","cited_by_count":23},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20},{"id":"2503.19740","title":"LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings","created":"2025-03-25","cited_by_count":20},{"id":"2503.17782","title":"GOAL: Global-local Object Alignment Learning","created":"2025-03-22","cited_by_count":17},{"id":"2606.31232","title":"Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding","created":"2026-06-30","cited_by_count":15},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11},{"id":"2303.17636","title":"Whether and When does Endoscopy Domain Pretraining Make Sense?","created":"2023-03-30","cited_by_count":8},{"id":"2401.00463","title":"Analyzing Local Representations of Self-supervised Vision Transformers","created":"2023-12-31","cited_by_count":8},{"id":"2404.00322","title":"Instrument-tissue Interaction Detection Framework for Surgical Video Understanding","created":"2024-03-30","cited_by_count":8},{"id":"2305.11451","title":"SurgMAE: Masked Autoencoders for Long Surgical Video Analysis","created":"2023-05-19","cited_by_count":7},{"id":"2505.10764","title":"SurgXBench: Explainable Vision-Language Model Benchmark for Surgery","created":"2025-05-16","cited_by_count":6},{"id":"2512.12678","title":"$\\beta$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment","created":"2025-12-14","cited_by_count":5},{"id":"2406.13210","title":"Surgical Triplet Recognition via Diffusion Model","created":"2024-06-19","cited_by_count":4},{"id":"2502.09653","title":"SASVi -- Segment Any Surgical Video","created":"2025-02-12","cited_by_count":4},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4},{"id":"2507.05020","title":"Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision","created":"2025-07-07","cited_by_count":3},{"id":"2501.15326","title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","created":"2025-01-25","cited_by_count":2},{"id":"2503.19670","title":"fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models","created":"2025-03-25","cited_by_count":2},{"id":"2403.19786","title":"Zero-shot Prompt-based Video Encoder for Surgical Gesture Recognition","created":"2024-03-28","cited_by_count":1},{"id":"2603.06999","title":"TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models","created":"2026-03-07","cited_by_count":1},{"id":"2603.16024","title":"Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery","created":"2026-03-17","cited_by_count":1},{"id":"2604.18134","title":"Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?","created":"2026-04-20","cited_by_count":1}],"next_cursor":null}