105 citations · 386 across the 27 of their papers we have counts for
27 papers
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
Nan Yin, Li Shen, Mengzhu Wang +5
Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costl…
PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction
Hao Wu, Fan Xu, Chong Chen +3
In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation…
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
Deyi Ji, Haoran Wang, Mingyuan Tao +3
Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture kno…
FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
Huafeng Liu, Pai Peng, Tao Chen +3
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-…
Rethinking IoU-based Optimization for Single-stage 3D Object Detection
Hualian Sheng, Sijia Cai, Na Zhao +5
Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and class…
Online Convolutional Re-parameterization
Mu Hu, Junyi Feng, Jiashen Hua +4
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inferenc…
Homography Loss for Monocular 3D Object Detection
Jiaqi Gu, Bojian Wu, Lubin Fan +4
Monocular 3D object detection is an essential task in autonomous driving. However, most current methods consider each 3D object in the scene as an independent training sample, whil…
PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting
Xiaoshuang Chen, Yiru Zhao, Yu Qin +4
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the…
Density-Based Clustering with Kernel Diffusion
Chao Zheng, Yingjie Chen, Chong Chen +2
Finding a suitable density function is essential for density-based clustering algorithms such as DBSCAN and DPC. A naive density corresponding to the indicator function of a unit $…
Improving 3D Object Detection with Channel-wise Transformer
Hualian Sheng, Sijia Cai, Yuan Liu +4
Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for e…
Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
Chenhang He, Jianqiang Huang, Xian-Sheng Hua +1
Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence o…
Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
Zhen Huang, Xu Shen, Jun Xing +6
Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged…
Criterion-based Heterogeneous Collaborative Filtering for Multi-behavior Implicit Recommendation
Xiao Luo, Daqing Wu, Yiyang Gu +7
Recent years have witnessed the explosive growth of interaction behaviors in multimedia information systems, where multi-behavior recommender systems have received increasing atten…
Discriminative-Generative Dual Memory Video Anomaly Detection
Xin Guo, Zhongming Jin, Chong Chen +5
Recently, people tried to use a few anomalies for video anomaly detection (VAD) instead of only normal data during the training process. A side effect of data imbalance occurs when…
Active Boundary Loss for Semantic Segmentation
Chi Wang, Yunke Zhang, Miaomiao Cui +6
This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries du…
DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
Xing Shen, Jirui Yang, Chunbo Wei +5
Binary grid mask representation is broadly used in instance segmentation. A representative instantiation is Mask R-CNN which predicts masks on a binary grid. Generall…
Causal Intervention for Weakly-Supervised Semantic Segmentation
Dong Zhang, Hanwang Zhang, Jinhui Tang +2
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only im…
Feature Pyramid Transformer
Dong Zhang, Hanwang Zhang, Jinhui Tang +3
Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are pass…
Out-of-distribution Generalization via Partial Feature Decorrelation
Xin Guo, Zhengxu Yu, Chao Xiang +5
Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribu…
Towards Fine-grained Human Pose Transfer with Detail Replenishing Network
Lingbo Yang, Pan Wang, Chang Liu +7
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality. For these applications, the…
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
Hongwei Yong, Jianqiang Huang, Xiansheng Hua +1
Optimization techniques are of great importance to effectively and efficiently train a deep neural network (DNN). It has been shown that using the first and second order statistics…
A Survey on Deep Hashing Methods
Xiao Luo, Haixin Wang, Daqing Wu +4
Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including compu…
SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation
Sheng Jin, Shangchen Zhou, Yao Liu +4
Deep hashing methods have been proved to be effective and efficient for large-scale Web media search. The success of these data-driven methods largely depends on collecting suffici…
Deep Active Learning for Video-based Person Re-identification
Menglin Wang, Baisheng Lai, Zhongming Jin +3
It is prohibitively expensive to annotate a large-scale video-based person re-identification (re-ID) dataset, which makes fully supervised methods inapplicable to real-world deploy…