{"list":"other","total":52,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"1604.02531","title":"Person Re-identification in the Wild","created":"2016-04-09","cited_by_count":157},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129},{"id":"1909.04538","title":"DeepPrivacy: A Generative Adversarial Network for Face Anonymization","created":"2019-09-10","cited_by_count":108},{"id":"2204.06890","title":"Clothes-Changing Person Re-identification with RGB Modality Only","created":"2022-04-14","cited_by_count":98},{"id":"2202.00443","title":"The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization","created":"2022-01-25","cited_by_count":95},{"id":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","cited_by_count":67},{"id":"2211.09454","title":"DeepPrivacy2: Towards Realistic Full-Body Anonymization","created":"2022-11-17","cited_by_count":51},{"id":"2209.06997","title":"M^4I: Multi-modal Models Membership Inference","created":"2022-09-15","cited_by_count":34},{"id":"2301.03046","title":"STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition","created":"2023-01-08","cited_by_count":29},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26},{"id":"2504.10825","title":"OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding","created":"2025-04-15","cited_by_count":22},{"id":"2302.08931","title":"LDFA: Latent Diffusion Face Anonymization for Self-driving Applications","created":"2023-02-17","cited_by_count":21},{"id":"2506.03179","title":"Vid-SME: Membership Inference Attacks against Large Video Understanding Models","created":"2025-05-29","cited_by_count":19},{"id":"2411.00762","title":"Face Anonymization Made Simple","created":"2024-11-01","cited_by_count":18},{"id":"2003.00813","title":"Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation","created":"2020-02-07","cited_by_count":13},{"id":"2306.05135","title":"Does Image Anonymization Impact Computer Vision Training?","created":"2023-06-08","cited_by_count":12},{"id":"2308.13093","title":"EgoBlur: Responsible Innovation in Aria","created":"2023-08-24","cited_by_count":12},{"id":"2309.04228","title":"FIVA: Facial Image and Video Anonymization and Anonymization Defense","created":"2023-09-08","cited_by_count":12},{"id":"2507.05675","title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","created":"2025-07-08","cited_by_count":9},{"id":"2207.11677","title":"Learnable Privacy-Preserving Anonymization for Pedestrian Images","created":"2022-07-24","cited_by_count":6},{"id":"2312.10930","title":"Deep Learning Approaches for Seizure Video Analysis: A Review","created":"2023-12-18","cited_by_count":6},{"id":"2507.07230","title":"Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement","created":"2025-07-09","cited_by_count":6},{"id":"2410.08551","title":"Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models","created":"2024-10-11","cited_by_count":3},{"id":"2506.16578","title":"SafeTriage: Facial Video De-identification for Privacy-Preserving Stroke Triage","created":"2025-06-19","cited_by_count":3},{"id":"2603.26336","title":"From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition","created":"2026-03-27","cited_by_count":2},{"id":"2408.11829","title":"FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification","created":"2024-08-06","cited_by_count":1},{"id":"2603.28605","title":"Unsafe2Safe: Controllable Image Anonymization for Downstream Utility","created":"2026-03-30","cited_by_count":1}],"next_cursor":null}