{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2006.11392","title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation","created":"2020-06-13","cited_by_count":460},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"2006.06485","title":"Deep Structural Causal Models for Tractable Counterfactual Inference","created":"2020-06-11","cited_by_count":211},{"id":"1906.10112","title":"GANalyze: Toward Visual Definitions of Cognitive Image Properties","created":"2019-06-24","cited_by_count":193},{"id":"1912.08142","title":"Causality matters in medical imaging","created":"2019-12-17","cited_by_count":193},{"id":"1903.07256","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","created":"2019-03-18","cited_by_count":171},{"id":"2504.04348","title":"OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning","created":"2025-04-06","cited_by_count":143},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"1903.08297","title":"Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening","created":"2019-03-20","cited_by_count":95},{"id":"2103.09712","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","created":"2021-03-17","cited_by_count":94},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90},{"id":"2011.12077","title":"CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection","created":"2020-11-24","cited_by_count":79},{"id":"1907.06099","title":"Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis","created":"2019-07-13","cited_by_count":76},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75},{"id":"2501.02955","title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","created":"2025-01-06","cited_by_count":70},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2103.03873","title":"OperA: Attention-Regularized Transformers for Surgical Phase Recognition","created":"2021-03-05","cited_by_count":60},{"id":"2401.14168","title":"Vivim: a Video Vision Mamba for Medical Video Segmentation","created":"2024-01-25","cited_by_count":52},{"id":"2306.05415","title":"Causal normalizing flows: from theory to practice","created":"2023-06-08","cited_by_count":51},{"id":"2004.08697","title":"CausalVAE: Structured Causal Disentanglement in Variational Autoencoder","created":"2020-04-18","cited_by_count":48},{"id":"1807.10565","title":"DeepPhase: Surgical Phase Recognition in CATARACTS Videos","created":"2018-07-17","cited_by_count":47},{"id":"2303.09962","title":"Adversarial Counterfactual Visual Explanations","created":"2023-03-17","cited_by_count":47},{"id":"2209.12148","title":"Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection","created":"2022-09-25","cited_by_count":34},{"id":"1612.05968","title":"Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification","created":"2016-12-18","cited_by_count":32},{"id":"2408.03867","title":"Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition","created":"2024-08-07","cited_by_count":32},{"id":"1802.03243","title":"RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations","created":"2018-02-09","cited_by_count":26},{"id":"2111.11044","title":"Exploring Segment-level Semantics for Online Phase Recognition from Surgical Videos","created":"2021-11-22","cited_by_count":23},{"id":"2403.20287","title":"Benchmarking Counterfactual Image Generation","created":"2024-03-29","cited_by_count":22},{"id":"2412.17920","title":"Causal Composition Diffusion Model for Closed-loop Traffic Generation","created":"2024-12-23","cited_by_count":22},{"id":"2203.12121","title":"Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection","created":"2022-03-23","cited_by_count":20},{"id":"2303.03052","title":"Masked Images Are Counterfactual Samples for Robust Fine-tuning","created":"2023-03-06","cited_by_count":20},{"id":"2310.13347","title":"NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding","created":"2023-10-20","cited_by_count":20},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19},{"id":"2410.08924","title":"DiffPO: A causal diffusion model for learning distributions of potential outcomes","created":"2024-10-11","cited_by_count":17},{"id":"2412.20651","title":"Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis","created":"2024-12-30","cited_by_count":13},{"id":"2503.14966","title":"Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models","created":"2025-03-19","cited_by_count":12},{"id":"2311.17833","title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","created":"2023-11-29","cited_by_count":11},{"id":"2410.14214","title":"MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging","created":"2024-10-18","cited_by_count":7},{"id":"2009.14406","title":"Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification","created":"2020-09-30","cited_by_count":6},{"id":"2410.23091","title":"CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense","created":"2024-10-30","cited_by_count":4},{"id":"2503.24108","title":"PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysis","created":"2025-03-31","cited_by_count":3},{"id":"2504.06088","title":"MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer","created":"2025-04-08","cited_by_count":2}],"next_cursor":null}