Fangrui Zhu
@Fangrui_Zhu
Followers
25
Following
23
Statuses
10
RT @praeclarumjj: 💠How do MLLMs improve their visual perception with more training data or visual inputs (depth/seg map)? 👉 Performance co…
0
10
0
Welcome to our poster at east exhibit hall 1711. Thanks my collaborators Huaizu @HuaizuJiang and Jianwei @jw2yang4ai !
#NeurIPS2024 Can we make SAM-like models to understand visual relationships? Excited to share FleVRS, which supports unified (HOI and scene graph), promotable, and open-vocabulary visual relationship segmentation. Paper: Code:
0
2
9
RT @HuaizuJiang: #NeurIPS2024 Can we make SAM-like models to understand visual relationships? Excited to share FleVRS, which supports unifi…
0
18
0
RT @MuCai7: Now TemporalBench is fully public! See how your video understanding model performs on TemporalBench before CVPR! 🤗 Dataset: h…
0
13
0
RT @jw2yang4ai: 🔥Check out our new LMM benchmark TemporalBench! Our world is temporal, dynamic and physical, which can be only captured i…
0
21
0
RT @HuaizuJiang: Excited to share our recent work HouseCrafter, which can lift a floorplan into a complete large 3D indoor scene (e.g. a ho…
0
6
0
Come and say hi at Arch 4A-E 10:30-noon on Thursday!!
#CVPR2024 We propose to solve zero-shot visual grounding by considering the structural similarities between images and captions, modeling the relationships of entities across two modalities. Paper: Code:
0
0
0
RT @HuaizuJiang: #CVPR2024 We propose to solve zero-shot visual grounding by considering the structural similarities between images and cap…
0
5
0
Check out our recent work in diagnosing human-object interaction detectors. The toolbox is simple and intuitive to use! Thank my advisor @HuaizuJiang for great advising and support! Thank @YimingXie4 @WeidiXie for meaningful discussions and advice!
Overwhelmed by the progress of human-object interaction (HOI) detection? Ever wondered why one HOI model performs better than another? Check out our recent work in diagnosing human-object interaction detectors. Paper: Code: 🛢️ 1/N
0
1
5