234 citations · 824 across the 36 of their papers we have counts for
34 papers · 1 filter
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Yuexiao Ma, Huixia Li, Xiawu Zheng +6
Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We ar…
FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation
Jie Qin, Jie Wu, Pengxiang Yan +8
Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more gen…
Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones
Cheng Cui, Ruoyu Guo, Yuning Du +10
Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning…
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
Peihao Chen, Deng Huang, Dongliang He +5
We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such…
Coherent Loss: A Generic Framework for Stable Video Segmentation
Mingyang Qian, Yi Fu, Xiao Tan +5
Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment. Due to the challenges associated with acquiring…
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
Di Hu, Rui Qian, Minyue Jiang +5
Discriminatively localizing sounding objects in cocktail-party, i.e., mixed sound scenes, is commonplace for humans, but still challenging for machines. In this paper, we propose a…
PP-YOLO: An Effective and Efficient Implementation of Object Detector
Xiang Long, Kaipeng Deng, Guanzhong Wang +8
Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary…
Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement
Jian Wang, Xiang Long, Yuan Gao +2
Recently, most of the state-of-the-art human pose estimation methods are based on heatmap regression. The final coordinates of keypoints are obtained by decoding heatmap directly.…
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Zhenbo Xu, Wei Zhang, Xiao Tan +5
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt convolutions for feature extraction. However, as affected by the i…
PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
Zhenbo Xu, Wei Zhang, Xiao Tan +7
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work…
Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
Liang Du, Xiaoqing Ye, Xiao Tan +4
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion…
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
Zhenbo Xu, Wei Zhang, Xiaoqing Ye +6
3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded o…
Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
Wenhao Wu, Dongliang He, Xiao Tan +3
Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a po…
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
Renchun You, Zhiyao Guo, Lei Cui +3
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between l…
Multi-Label Classification with Label Graph Superimposing
Ya Wang, Dongliang He, Fu Li +4
Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep lea…
Dynamic Instance Normalization for Arbitrary Style Transfer
Yongcheng Jing, Xiao Liu, Yukang Ding +4
Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way. Such manually-defi…
TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation
Fan Yang, Xiao Liu, Dongliang He +5
In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into mul…
Perspective-Guided Convolution Networks for Crowd Counting
Zhaoyi Yan, Yuchen Yuan, Wangmeng Zuo +4
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i.e. PGCNet), which aims to overcome the dramati…
Image Inpainting with Learnable Bidirectional Attention Maps
Chaohao Xie, Shaohui Liu, Chao Li +5
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular ho…
Deep Concept-wise Temporal Convolutional Networks for Action Localization
Xin Li, Tianwei Lin, Xiao Liu +7
Existing action localization approaches adopt shallow temporal convolutional networks (\ie, TCN) on 1D feature map extracted from video frames. In this paper, we empirically find t…
Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
Wenhao Wu, Dongliang He, Xiao Tan +2
Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. How…
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
Tianwei Lin, Xiao Liu, Xin Li +2
Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-…
Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution
Chao Li, Dongliang He, Xiao Liu +2
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks. However, there has been li…
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Ming Liu, Yukang Ding, Min Xia +4
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually…