VamosC / CoLearning-meet-StitchUp
[TIP 2023] Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition.
☆13Updated last year
Related projects: ⓘ
- The official code for [ACM MM 2022] 'In-N-Out Generative Learning for Dense Unsupervised Video Segmentation'.☆20Updated last year
- TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment☆13Updated 3 months ago
- ☆38Updated 9 months ago
- Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes☆18Updated last year
- Benchmarking and Analyzing Generative Data for Visual Recognition☆26Updated last year
- The benchmark for "Video Object Segmentation in Panoptic Wild Scenes".☆11Updated 11 months ago
- Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation (ICCV 2023)☆61Updated 11 months ago
- The offical implemention of JM3D.☆27Updated 11 months ago
- Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation☆38Updated last month
- [ICLR 2024] Official implementation of the paper "Toss: High-quality text-guided novel view synthesis from a single image"☆14Updated 4 months ago
- ☆41Updated this week
- [CVPR 2024] The official implementation of paper "Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training"☆24Updated 4 months ago
- (ICCV 2023) Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation☆43Updated 2 months ago
- ☆57Updated last year
- DMAOT ranked 1st in the VOTS 2023 challenge.☆12Updated 8 months ago
- Official implementation of “JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery“☆34Updated last year
- ICCV2023-Diffusion-Papers☆110Updated last year
- ☆56Updated last year
- Code for the paper "Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundatio…☆22Updated 10 months ago
- Official implementation of PARIS3D (Accepted to ECCV 2024).☆18Updated last week
- ☆44Updated last year
- An innovative method designed to augment the capabilities of existing video diffusion models☆20Updated 4 months ago
- ☆30Updated 6 months ago
- ☆20Updated last year
- ☆13Updated this week
- ☆22Updated 2 months ago
- [CVPR 2024] BIVDiff: A Training-free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models☆49Updated last week
- Official implementation of MTM☆20Updated last year
- ☆26Updated last week
- Official code for CVPR 2024 paper: Discriminative Probing and Tuning for Text-to-Image Generation☆23Updated 2 weeks ago