most citedDIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

2 citations · 3 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV2024

ToMiE: Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars

Yifan Zhan, Qingtian Zhu, Muyao Niu +6

In this paper, we highlight a critical yet often overlooked factor in most 3D human tasks, namely modeling complicated 3D human with with hand-held objects or loose-fitting clothin…

cs.CV20242 cited

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

Hao Wu, Huabin Liu, Yu Qiao +1

We present Dive Into the BoundarieS (DIBS), a novel pretraining framework for dense video captioning (DVC), that elaborates on improving the quality of the generated event captions…

cs.CV2024

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

Yutong Chen, Yifan Zhan, Zhihang Zhong +4

Neural rendering techniques have significantly advanced 3D human body modeling. However, previous approaches often overlook dynamics induced by factors such as motion inertia, lead…

cs.CV20241 cited

Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption

Ziteng Cui, Lin Gu, Xiao Sun +3

The standard Neural Radiance Fields (NeRF) paradigm employs a viewer-centered methodology, entangling the aspects of illumination and material reflectance into emission solely from…

cs.CV2023

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

Yuchen Yang, Yu Qiao, Xiao Sun

Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision. In a supervised manner, approaches heavily rely on laborio…

cs.CV2023

Velocity Disambiguation for Video Frame Interpolation

Zhihang Zhong, Yiming Zhang, Wei Wang +5

Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movement…