{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"1612.07659","title":"Structured Sequence Modeling with Graph Convolutional Recurrent Networks","created":"2016-12-22","cited_by_count":275},{"id":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"2303.12346","title":"NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation","created":"2023-03-22","cited_by_count":171},{"id":"2008.00334","title":"Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning","created":"2020-08-01","cited_by_count":91},{"id":"2304.01168","title":"DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving","created":"2023-04-03","cited_by_count":73},{"id":"1903.00618","title":"Unsupervised Traffic Accident Detection in First-Person Videos","created":"2019-03-02","cited_by_count":70},{"id":"1912.12148","title":"DADA: Driver Attention Prediction in Driving Accident Scenarios","created":"2019-12-18","cited_by_count":70},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68},{"id":"2003.03923","title":"Deconfounded Image Captioning: A Causal Retrospect","created":"2020-03-09","cited_by_count":65},{"id":"1711.06406","title":"Predicting Driver Attention in Critical Situations","created":"2017-11-17","cited_by_count":61},{"id":"1804.02675","title":"Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB","created":"2018-04-08","cited_by_count":51},{"id":"2307.12616","title":"CTVIS: Consistent Training for Online Video Instance Segmentation","created":"2023-07-24","cited_by_count":51},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51},{"id":"2107.10189","title":"DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation","created":"2021-07-21","cited_by_count":46},{"id":"2403.00436","title":"Abductive Ego-View Accident Video Understanding for Safe Driving Perception","created":"2024-03-01","cited_by_count":43},{"id":"1809.07408","title":"Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems","created":"2018-09-19","cited_by_count":42},{"id":"2106.10197","title":"A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents","created":"2021-06-18","cited_by_count":42},{"id":"2308.15985","title":"Vision-Based Traffic Accident Detection and Anticipation: A Survey","created":"2023-08-30","cited_by_count":31},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22},{"id":"1810.09044","title":"VIENA2: A Driving Anticipation Dataset","created":"2018-10-22","cited_by_count":19},{"id":"2111.07839","title":"Learnable Locality-Sensitive Hashing for Video Anomaly Detection","created":"2021-11-15","cited_by_count":17},{"id":"2302.02316","title":"Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":17},{"id":"2308.01537","title":"Learning Causality-inspired Representation Consistency for Video Anomaly Detection","created":"2023-08-03","cited_by_count":17},{"id":"2305.04224","title":"Visual Causal Scene Refinement for Video Question Answering","created":"2023-05-07","cited_by_count":16},{"id":"2112.00475","title":"Weakly-Supervised Video Object Grounding via Causal Intervention","created":"2021-12-01","cited_by_count":13},{"id":"2302.02327","title":"Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition","created":"2023-02-05","cited_by_count":11},{"id":"2206.04879","title":"Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion","created":"2022-06-10","cited_by_count":8},{"id":"2303.01000","title":"X&Fuse: Fusing Visual Information in Text-to-Image Generation","created":"2023-03-02","cited_by_count":6}],"next_cursor":null}