{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"AOT-GAN-for-Inpainting","owner":"researchmm","isFork":false,"description":"[TVCG'2023] AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)","allTopics":["codebase","high-resolution","image-inpainting","multi-scale"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":10,"starsCount":382,"forksCount":61,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T05:03:48.849Z"}},{"type":"Public","name":"Stark","owner":"researchmm","isFork":false,"description":"[ICCV'21] Learning Spatio-Temporal Transformer for Visual Tracking","allTopics":["transformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":71,"starsCount":618,"forksCount":140,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-13T07:02:29.763Z"}},{"type":"Public","name":"MM-Diffusion","owner":"researchmm","isFork":false,"description":"[CVPR'23] MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","allTopics":["video-generation","multi-modality","diffusion-models","content-creation","audio-generation"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":14,"starsCount":344,"forksCount":23,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-15T03:02:48.387Z"}},{"type":"Public","name":"VQD-SR","owner":"researchmm","isFork":false,"description":"[ICCV'23] VQD-SR: Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution","allTopics":["animation","super-resolution"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":4,"starsCount":32,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-18T08:56:50.297Z"}},{"type":"Public","name":"TracKit","owner":"researchmm","isFork":false,"description":"[ECCV'20] Ocean: Object-aware Anchor-Free Tracking","allTopics":["tracking","anchor-free","eccv2020","segmentation"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":28,"starsCount":603,"forksCount":99,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-07T23:50:10.244Z"}},{"type":"Public","name":"davinci-videofactory","owner":"researchmm","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":12,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-17T14:22:38.707Z"}},{"type":"Public","name":"FTVSR","owner":"researchmm","isFork":false,"description":"[ECCV'22] FTVSR: Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution","allTopics":["video-super-resolution","video-restoration"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":14,"starsCount":148,"forksCount":13,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-13T11:11:51.901Z"}},{"type":"Public","name":"language-guided-animation","owner":"researchmm","isFork":false,"description":"[TMM 2023] Language-Guided Face Animation by Recurrent StyleGAN-based Generator","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":10,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-23T02:07:22.239Z"}},{"type":"Public","name":"AI_Illustrator","owner":"researchmm","isFork":false,"description":"[MM'22 Oral] AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":11,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-03T09:07:37.591Z"}},{"type":"Public","name":"STTR","owner":"researchmm","isFork":false,"description":"[ACCV'22] Fine-Grained Image Style Transfer with Visual Transformers","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":12,"forksCount":5,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-12-06T16:00:18.364Z"}},{"type":"Public","name":"soho","owner":"researchmm","isFork":false,"description":"[CVPR'21 Oral] Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":9,"starsCount":206,"forksCount":19,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-30T05:49:37.190Z"}},{"type":"Public","name":"TTSR","owner":"researchmm","isFork":false,"description":"[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution","allTopics":["image-restoration","image-super-resolution"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":751,"forksCount":116,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-07-24T05:04:00.969Z"}},{"type":"Public","name":"TTVSR","owner":"researchmm","isFork":false,"description":"[CVPR'22 Oral] TTVSR: Learning Trajectory-Aware Transformer for Video Super-Resolution","allTopics":["video-super-resolution","video-restoration"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":9,"starsCount":193,"forksCount":12,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-07-24T05:03:57.579Z"}},{"type":"Public","name":"CKDN","owner":"researchmm","isFork":false,"description":"[ICCV'21] CKDN: Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":55,"forksCount":5,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-04-09T06:48:29.667Z"}},{"type":"Public","name":"CyDAS","owner":"researchmm","isFork":false,"description":"Cyclic Differentiable Architecture Search","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":33,"forksCount":6,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-02-14T08:31:29.165Z"}},{"type":"Public","name":"LightTrack","owner":"researchmm","isFork":false,"description":"[CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search","allTopics":["efficient","nas","cvpr2021"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":21,"starsCount":383,"forksCount":58,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-12-29T08:19:42.331Z"}},{"type":"Public","name":"tasn","owner":"researchmm","isFork":false,"description":"Trilinear Attention Sampling Network for Fine-grained Image Recognition","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":6,"issueCount":16,"starsCount":219,"forksCount":40,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-12-14T21:36:40.956Z"}},{"type":"Public","name":"PEN-Net-for-Inpainting","owner":"researchmm","isFork":false,"description":"[CVPR'2019] PEN-Net: Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting ","allTopics":["attention","attention-transfer-network","image-inpainting","pen-net"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":23,"starsCount":351,"forksCount":76,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-11-29T20:51:39.653Z"}},{"type":"Public","name":"generate-it","owner":"researchmm","isFork":false,"description":"A collection of models for image<->text generation in ACM MM 2021.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":64,"forksCount":8,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-10-31T09:13:25.672Z"}},{"type":"Public","name":"AAST-pytorch","owner":"researchmm","isFork":false,"description":"[MM'20] Aesthetic-Aware Image Style Transfer","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":14,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-09-16T15:33:04.467Z"}},{"type":"Public","name":"img2poem","owner":"researchmm","isFork":false,"description":"[MM'18] Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training","allTopics":["code","dataset","poem-generator"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":282,"forksCount":62,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-08-23T03:00:09.907Z"}},{"type":"Public","name":"STTN","owner":"researchmm","isFork":false,"description":"[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting","allTopics":["transformer","spatial-temporal","video-inpainting","completing-videos"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":1,"issueCount":10,"starsCount":438,"forksCount":73,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-07-26T17:02:19.920Z"}},{"type":"Public","name":"AutoML","owner":"researchmm","isFork":true,"description":"AutoFormer, Cream","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":220,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-07-04T13:46:25.991Z"}},{"type":"Public","name":"SiamDW","owner":"researchmm","isFork":false,"description":"[CVPR'19 Oral] Deeper and Wider Siamese Networks for Real-Time Visual Tracking","allTopics":["tracking"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":19,"starsCount":747,"forksCount":179,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-05-18T03:53:58.966Z"}},{"type":"Public","name":"SariGAN","owner":"researchmm","isFork":false,"description":"[NeurIPS'20] Learning Semantic-aware Normalization for Generative Adversarial Networks","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":54,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-05-14T09:12:01.857Z"}},{"type":"Public","name":"NEAS","owner":"researchmm","isFork":false,"description":"","allTopics":["nas"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":19,"forksCount":5,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-05-11T13:36:32.148Z"}},{"type":"Public","name":"WSOD2","owner":"researchmm","isFork":false,"description":"[ICCV'19] WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":4,"starsCount":46,"forksCount":3,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-01-26T07:43:50.012Z"}},{"type":"Public","name":"2D-TAN-Microsoft","owner":"researchmm","isFork":true,"description":"[AAAI‘20] - Learning 2D Temporal Localization Networks for Moment Localization with Natural Language","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":0,"forksCount":157,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-02-16T01:58:27.818Z"}},{"type":"Public","name":"DBTNet","owner":"researchmm","isFork":false,"description":"Code for our NeurIPS'19 paper \"Learning Deep Bilinear Transformation for Fine-grained Image Representation\"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":105,"forksCount":18,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-01-20T02:23:36.879Z"}},{"type":"Public","name":"2D-TAN","owner":"researchmm","isFork":false,"description":"AAAI2020 - Learning 2D Temporal Localization Networks for Moment Localization with Natural Language","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":16,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-12-10T02:14:54.528Z"}}],"repositoryCount":31,"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"}