{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"LOVA3","owner":"showlab","isFork":false,"description":"The official repo of \"Learning to Visual Question Answering, Asking and Assessment\"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-24T11:18:29.585Z"}},{"type":"Public","name":"BoxDiff","owner":"showlab","isFork":false,"description":"[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","topicNames":["text-to-image-synthesis","diffusion-models"],"topicsNotShown":0,"allTopics":["text-to-image-synthesis","diffusion-models"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":213,"forksCount":11,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-15T01:52:41.350Z"}},{"type":"Public","name":"EgoVLP","owner":"showlab","isFork":false,"description":"[NeurIPS2022] Egocentric Video-Language Pretraining","topicNames":["pretraining","video-language","egocentric-vision","pytorch"],"topicsNotShown":0,"allTopics":["pretraining","video-language","egocentric-vision","pytorch"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":208,"forksCount":19,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-09T05:52:12.512Z"}},{"type":"Public","name":"UniVTG","owner":"showlab","isFork":false,"description":"[ICCV2023] UniVTG: Towards Unified Video-Language Temporal Grounding","topicNames":["video-summarization","video-grounding","pretraining","moment-retrieval","highlight-detection","video-language"],"topicsNotShown":0,"allTopics":["video-summarization","video-grounding","pretraining","moment-retrieval","highlight-detection","video-language"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":17,"starsCount":288,"forksCount":21,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T15:15:34.433Z"}},{"type":"Public","name":"VisorGPT","owner":"showlab","isFork":false,"description":"[NeurIPS 2023] Customize spatial layouts for conditional image synthesis models, e.g., ControlNet, using GPT","topicNames":["image-generation","gpt","diffusion-models","controlnet"],"topicsNotShown":0,"allTopics":["image-generation","gpt","diffusion-models","controlnet"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":4,"starsCount":126,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-04T01:51:17.676Z"}},{"type":"Public","name":"Long-form-Video-Prior","owner":"showlab","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":20,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-03T03:09:13.211Z"}},{"type":"Public","name":"X-Adapter","owner":"showlab","isFork":false,"description":"[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":14,"starsCount":675,"forksCount":38,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-23T12:19:42.629Z"}},{"type":"Public","name":"DragAnything","owner":"showlab","isFork":false,"description":"Official code for 'DragAnything: Motion Control for Anything using Entity Representation'","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":16,"starsCount":314,"forksCount":10,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-10T05:56:10.797Z"}},{"type":"Public","name":"cosmo","owner":"showlab","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":2,"starsCount":66,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-10T21:04:11.443Z"}},{"type":"Public","name":"sparseformer","owner":"showlab","isFork":false,"description":"(ICLR 2024, CVPR 2024) SparseFormer ","topicNames":["computer-vision","transformer","efficient-neural-networks","vision-transformer","sparseformer"],"topicsNotShown":0,"allTopics":["computer-vision","transformer","efficient-neural-networks","vision-transformer","sparseformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":61,"forksCount":1,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-30T09:22:01.830Z"}},{"type":"Public","name":"CLVQA","owner":"showlab","isFork":false,"description":"[AAAI2023] Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task (Oral)","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":33,"forksCount":5,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-23T02:59:59.402Z"}},{"type":"Public","name":"MotionDirector","owner":"showlab","isFork":false,"description":"MotionDirector: Motion Customization of Text-to-Video Diffusion Models.","topicNames":["video-generation","diffusion-models","text-to-video","text-to-motion","text-to-video-generation","motion-customization"],"topicsNotShown":0,"allTopics":["video-generation","diffusion-models","text-to-video","text-to-motion","text-to-video-generation","motion-customization"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":19,"starsCount":714,"forksCount":42,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-03T07:07:11.091Z"}},{"type":"Public","name":"Efficient-CLS","owner":"showlab","isFork":false,"description":"[ICCV 2023] Label-Efficient Online Continual Object Detection in Streaming Video","topicNames":["video-streaming","continual-learning","online-continual-learning","label-efficient","object-detection"],"topicsNotShown":0,"allTopics":["video-streaming","continual-learning","online-continual-learning","label-efficient","object-detection"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":16,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-08T09:13:37.805Z"}},{"type":"Public","name":"DatasetDM","owner":"showlab","isFork":false,"description":"[NeurIPS2023] DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":16,"starsCount":286,"forksCount":12,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-03T10:56:51.428Z"}},{"type":"Public","name":"Show-1","owner":"showlab","isFork":false,"description":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":8,"issueCount":8,"starsCount":1069,"forksCount":63,"license":"Other","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,5,0,12,13,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-30T12:21:36.631Z"}},{"type":"Public","name":"loveu-tgve-2023","owner":"showlab","isFork":false,"description":"Official GitHub repository for the Text-Guided Video Editing (TGVE) competition of LOVEU Workshop @ CVPR'23.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":65,"forksCount":9,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-25T07:38:10.536Z"}},{"type":"Public","name":"Tune-A-Video","owner":"showlab","isFork":false,"description":"[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":31,"starsCount":4111,"forksCount":370,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-25T02:00:06.557Z"}},{"type":"Public","name":"datacentric.vlp","owner":"showlab","isFork":false,"description":"Compress conventional Vision-Language Pre-training data","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":49,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-09-22T05:02:47.464Z"}},{"type":"Public","name":"SCT","owner":"showlab","isFork":false,"description":"[IJCV2023] Offical implementation of \"SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels\"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":9,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-09-18T12:40:57.934Z"}},{"type":"Public","name":"VLog","owner":"showlab","isFork":false,"description":"Transform Video as a Document with ChatGPT, CLIP, BLIP2, GRIT, Whisper, LangChain.","topicNames":["whisper","video-language","chatgpt","langchain","large-language-model"],"topicsNotShown":0,"allTopics":["whisper","video-language","chatgpt","langchain","large-language-model"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":493,"forksCount":20,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-25T05:14:55.122Z"}},{"type":"Public","name":"Q2A","owner":"showlab","isFork":false,"description":"[ECCV 2022] AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":18,"forksCount":6,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-31T03:58:26.690Z"}},{"type":"Public","name":"Image2Paragraph","owner":"showlab","isFork":false,"description":"[A toolbox for fun.] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.","topicNames":["toolbox","gpt4","chatgpt","segmentt-anything"],"topicsNotShown":0,"allTopics":["toolbox","gpt4","chatgpt","segmentt-anything"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":15,"starsCount":765,"forksCount":51,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-28T06:41:05.411Z"}},{"type":"Public","name":"afformer","owner":"showlab","isFork":false,"description":"Affordance Grounding from Demonstration Video to Target Image (CVPR 2023)","topicNames":["deep-learning","pytorch"],"topicsNotShown":0,"allTopics":["deep-learning","pytorch"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":33,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-28T06:42:13.474Z"}},{"type":"Public","name":"all-in-one","owner":"showlab","isFork":false,"description":"[CVPR2023] All in One: Exploring Unified Video-Language Pre-training","topicNames":["pytorch","codebase","pre-training","video-language"],"topicsNotShown":0,"allTopics":["pytorch","codebase","pre-training","video-language"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":4,"starsCount":273,"forksCount":16,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-25T11:46:31.408Z"}},{"type":"Public","name":"AVA-AVD","owner":"showlab","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":13,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-11-24T02:39:42.174Z"}},{"type":"Public","name":"DeVRF","owner":"showlab","isFork":false,"description":"The Pytorch implementation of \"DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes\"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":178,"forksCount":12,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-10-17T12:38:51.820Z"}},{"type":"Public","name":"GEB-Plus","owner":"showlab","isFork":false,"description":"[ECCV 2022] GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":16,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-08-24T10:22:17.993Z"}},{"type":"Public","name":"Region_Learner","owner":"showlab","isFork":false,"description":"The Pytorch implementation for \"Video-Text Pre-training with Learned Regions\"","topicNames":["video-language"],"topicsNotShown":0,"allTopics":["video-language"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":42,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-07-15T11:15:33.988Z"}},{"type":"Public","name":"DemoVLP","owner":"showlab","isFork":false,"description":"[Arxiv2022] Revitalize Region Feature for Democratizing Video-Language Pre-training","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":21,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-03-19T10:03:13.175Z"}}],"repositoryCount":29,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}