794 citations · 5.6k across the 185 of their papers we have counts for
32 papers · 2 filters
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images
Yuan Yao, Yuanhan Zhang, Zhenfei Yin +3
The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training…
MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency
Mingye Xu, Mutian Xu, Tong He +4
Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains a…
EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder
Xiaoshui Huang, Zhou Huang, Sheng Li +5
The pretrain-finetune paradigm has achieved great success in NLP and 2D image fields because of the high-quality representation ability and transferability of their pretrained mode…
GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds
Honghui Yang, Tong He, Jiaheng Liu +5
Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks such as image and video, exploring MAE in large-scale 3D point clouds remains challenging du…
Reconstructing Hand-Held Objects from Monocular Video
Di Huang, Xiaopeng Ji, Xingyi He +5
This paper presents an approach that reconstructs a hand-held object from a monocular video. In contrast to many recent methods that directly predict object geometry by a trained n…
3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
Jiaheng Liu, Tong He, Honghui Yang +6
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of…
Boosting Semi-Supervised 3D Object Detection with Semi-Sampling
Xiaopei Wu, Yang Zhao, Liang Peng +6
Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D obj…
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Jingru Tan, Bo Li, Xin Lu +4
Long-tail distribution is widely spread in real-world applications. Due to the extremely small ratio of instances, tail categories often show inferior accuracy. In this paper, we f…
Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing
Peng Ye, Shengji Tang, Baopu Li +2
Residual networks have shown great success and become indispensable in today's deep models. In this work, we aim to re-investigate the training process of residual networks from a…
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
Tianyu Huang, Bowen Dong, Yunhan Yang +4
Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language pre-training models to 3D vi…
Towards Frame Rate Agnostic Multi-Object Tracking
Weitao Feng, Lei Bai, Yongqiang Yao +2
Multi-Object Tracking (MOT) is one of the most fundamental computer vision tasks that contributes to various video analysis applications. Despite the recent promising progress, cur…
ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
Lumin Xu, Sheng Jin, Wentao Liu +4
This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We p…
An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection
Xinzhu Ma, Yuan Meng, Yinmin Zhang +4
Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main…
Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation
Peng Ye, Baopu Li, Tao Chen +6
Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal n…
3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal
Hao Meng, Sheng Jin, Wentao Liu +4
Estimating 3D interacting hand pose from a single RGB image is essential for understanding human actions. Unlike most previous works that directly predict the 3D poses of two inter…
NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition
Boyang Xia, Wenhao Wu, Haoran Wang +5
It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video re…
Pose for Everything: Towards Category-Agnostic Pose Estimation
Lumin Xu, Sheng Jin, Wang Zeng +5
Existing works on 2D pose estimation mainly focus on a certain category, e.g. human, animal, and vehicle. However, there are lots of application scenarios that require detecting th…
Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches
Yuanzheng Ci, Chen Lin, Lei Bai +1
Contrastive-based self-supervised learning methods achieved great success in recent years. However, self-supervision requires extremely long training epochs (e.g., 800 epochs for M…
Fine-grained Retrieval Prompt Tuning
Shijie Wang, Jianlong Chang, Zhihui Wang +3
Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise simil…
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
Wenhao Wu, Zhun Sun, Wanli Ouyang
Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational cap…
TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer
Jiajun Deng, Zhengyuan Yang, Daqing Liu +5
In this work, we explore neat yet effective Transformer-based frameworks for visual grounding. The previous methods generally address the core problem of visual grounding, i.e., mu…
Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains
Haiyang Yang, Meilin Chen, Yizhou Wang +5
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised lea…
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation
Zengyu Qiu, Xinzhu Ma, Kunlin Yang +4
Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the…
Unsupervised Learning of Accurate Siamese Tracking
Qiuhong Shen, Lei Qiao, Jinyang Guo +7
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial s…