794 citations · 4.8k across the 152 of their papers we have counts for
30 papers · 1 filter
CARAFE++: Unified Content-Aware ReAssembly of FEatures
Jiaqi Wang, Kai Chen, Rui Xu +3
Feature reassembly, i.e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e.g., residual networks and feature pyra…
FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds
Tai Wang, Conghui He, Zhe Wang +2
Recent years have witnessed the rapid progress of perception algorithms on top of LiDAR, a widely adopted sensor for autonomous driving systems. These LiDAR-based solutions are typ…
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
Xinge Zhu, Hui Zhou, Tai Wang +5
State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corpora…
Understanding the wiring evolution in differentiable neural architecture search
Sirui Xie, Shoukang Hu, Xinjiang Wang +4
Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underl…
A Unified Framework for Shot Type Classification Based on Subject Centric Lens
Anyi Rao, Jiaze Wang, Linning Xu +4
Shots are key narrative elements of various videos, e.g. movies, TV series, and user-generated videos that are thriving over the Internet. The types of shots greatly influence how…
Online Multi-modal Person Search in Videos
Jiangyue Xia, Anyi Rao, Qingqiu Huang +3
The task of searching certain people in videos has seen increasing potential in real-world applications, such as video organization and editing. Most existing approaches are devise…
Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation
Hui Zhou, Xinge Zhu, Xiao Song +4
State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. The projection methods includes spher…
Seesaw Loss for Long-Tailed Instance Segmentation
Jiaqi Wang, Wenwei Zhang, Yuhang Zang +7
Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category dist…
MovieNet: A Holistic Dataset for Movie Understanding
Qingqiu Huang, Yu Xiong, Anyi Rao +2
Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In th…
Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation
Hang Zhou, Xudong Xu, Dahua Lin +2
Stereophonic audio is an indispensable ingredient to enhance human auditory experience. Recent research has explored the usage of visual information as guidance to generate binaura…
Learn to Propagate Reliably on Noisy Affinity Graphs
Lei Yang, Qingqiu Huang, Huaiyi Huang +2
Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual re…
Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations
Huaiyi Huang, Yuqi Zhang, Qingqiu Huang +3
Place is an important element in visual understanding. Given a photo of a building, people can often tell its functionality, e.g. a restaurant or a shop, its cultural style, e.g. A…
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
Tong Wu, Qingqiu Huang, Ziwei Liu +2
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional sin…
Intra- and Inter-Action Understanding via Temporal Action Parsing
Dian Shao, Yue Zhao, Bo Dai +1
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrat…
Novel Policy Seeking with Constrained Optimization
Hao Sun, Zhenghao Peng, Bo Dai +3
In problem-solving, we humans can come up with multiple novel solutions to the same problem. However, reinforcement learning algorithms can only produce a set of monotonous policie…
Evolutionary Stochastic Policy Distillation
Hao Sun, Xinyu Pan, Bo Dai +2
Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging reinforcement learning problem due to the sparsity of reward signals. In this work, we propose a new formula…
Motion Guided 3D Pose Estimation from Videos
Jingbo Wang, Sijie Yan, Yuanjun Xiong +1
We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose. In computing motion loss, a simple yet effective representat…
A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
Anyi Rao, Linning Xu, Yu Xiong +4
Scene, as the crucial unit of storytelling in movies, contains complex activities of actors and their interactions in a physical environment. Identifying the composition of scenes…
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
Dian Shao, Yue Zhao, Bo Dai +1
On public benchmarks, current action recognition techniques have achieved great success. However, when used in real-world applications, e.g. sport analysis, which requires the capa…
Feature Pyramid Grids
Kai Chen, Yuhang Cao, Chen Change Loy +2
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale. In this paper, w…
Self-Supervised Scene De-occlusion
Xiaohang Zhan, Xingang Pan, Bo Dai +3
Natural scene understanding is a challenging task, particularly when encountering images of multiple objects that are partially occluded. This obstacle is given rise by varying obj…
SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Xinge Zhu, Yuexin Ma, Tai Wang +3
Multi-class 3D object detection aims to localize and classify objects of multiple categories from point clouds. Due to the nature of point clouds, i.e. unstructured, sparse and noi…
Learning to Cluster Faces via Confidence and Connectivity Estimation
Lei Yang, Dapeng Chen, Xiaohang Zhan +3
Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that su…
Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds
Tai Wang, Xinge Zhu, Dahua Lin
LiDAR is an important method for autonomous driving systems to sense the environment. The point clouds obtained by LiDAR typically exhibit sparse and irregular distribution, thus p…