1.9k citations · 3k across the 38 of their papers we have counts for
38 papers
InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation
Fei He, Haoyang Zhang, Naiyu Gao +4
Video instance segmentation (VIS) aims at segmenting and tracking objects in videos. Prior methods typically generate frame-level or clip-level object instances first and then asso…
Learning Disentangled Label Representations for Multi-label Classification
Jian Jia, Fei He, Naiyu Gao +2
Although various methods have been proposed for multi-label classification, most approaches still follow the feature learning mechanism of the single-label (multi-class) classifica…
QueryProp: Object Query Propagation for High-Performance Video Object Detection
Fei He, Naiyu Gao, Jian Jia +2
Video object detection has been an important yet challenging topic in computer vision. Traditional methods mainly focus on designing the image-level or box-level feature propagatio…
RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning
Hao Chen, Guangkai Yang, Junge Zhang +2
In recent years, reinforcement learning has faced several challenges in the multi-agent domain, such as the credit assignment issue. Value function factorization emerges as a promi…
PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
Naiyu Gao, Fei He, Jian Jia +4
This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior w…
SOTVerse: A User-defined Task Space of Single Object Tracking
Shiyu Hu, Xin Zhao, Kaiqi Huang
Single object tracking (SOT) research falls into a cycle -- trackers perform well on most benchmarks but quickly fail in challenging scenarios, causing researchers to doubt the ins…
Split Semantic Detection in Sandplay Images
Xiaokun Feng, Xiaotang Chen, Jian Jia +1
Sandplay image, as an important psychoanalysis carrier, is a visual scene constructed by the client selecting and placing sand objects (e.g., sand, river, human figures, animals, v…
Global Instance Tracking: Locating Target More Like Humans
Shiyu Hu, Xin Zhao, Lianghua Huang +1
Target tracking, the essential ability of the human visual system, has been simulated by computer vision tasks. However, existing trackers perform well in austere experimental envi…
DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Games
Qibin Zhou, Dongdong Bai, Junge Zhang +2
An imperfect-information game is a type of game with asymmetric information. It is more common in life than perfect-information game. Artificial intelligence (AI) in imperfect-info…
The Partially Observable Asynchronous Multi-Agent Cooperation Challenge
Meng Yao, Qiyue Yin, Jun Yang +5
Multi-agent reinforcement learning (MARL) has received increasing attention for its applications in various domains. Researchers have paid much attention on its partially observabl…
Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition
Jian Jia, Xiaotang Chen, Kaiqi Huang
While recent studies on pedestrian attribute recognition have shown remarkable progress in leveraging complicated networks and attention mechanisms, most of them neglect the inter-…
Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
Jian Jia, Houjing Huang, Xiaotang Chen +1
Pedestrian attribute recognition aims to assign multiple attributes to one pedestrian image captured by a video surveillance camera. Although numerous methods are proposed and make…
Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
Wenzhen Huang, Qiyue Yin, Junge Zhang +1
Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inacc…
Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
Naiyu Gao, Yanhu Shan, Xin Zhao +1
Panoptic segmentation (PS) is a complex scene understanding task that requires providing high-quality segmentation for both thing objects and stuff regions. Previous methods handle…
Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method
Jian Jia, Houjing Huang, Wenjie Yang +2
Despite various methods are proposed to make progress in pedestrian attribute recognition, a crucial problem on existing datasets is often neglected, namely, a large number of iden…
GlobalTrack: A Simple and Strong Baseline for Long-term Tracking
Lianghua Huang, Xin Zhao, Kaiqi Huang
A key capability of a long-term tracker is to search for targets in very large areas (typically the entire image) to handle possible target absences or tracking failures. However,…
SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Naiyu Gao, Yanhu Shan, Yupei Wang +4
Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnost…
MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
Zihao Li, Shu Zhang, Junge Zhang +3
Universal lesion detection (ULD) on computed tomography (CT) images is an important but underdeveloped problem. Recently, deep learning-based approaches have been proposed for ULD,…
Point Cloud Super Resolution with Adversarial Residual Graph Networks
Huikai Wu, Junge Zhang, Kaiqi Huang
Point cloud super-resolution is a fundamental problem for 3D reconstruction and 3D data understanding. It takes a low-resolution (LR) point cloud as input and generates a high-reso…
SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
Huikai Wu, Junge Zhang, Kaiqi Huang
In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder style and focus on design…
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Huikai Wu, Junge Zhang, Kaiqi Huang +2
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity a…
3D Object Detection Using Scale Invariant and Feature Reweighting Networks
Xin Zhao, Zhe Liu, Ruolan Hu +1
3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real sc…
EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Houjing Huang, Wenjie Yang, Xiaotang Chen +5
Person re-identification (ReID) has achieved significant improvement under the single-domain setting. However, directly exploiting a model to new domains is always faced with huge…
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
Lianghua Huang, Xin Zhao, Kaiqi Huang
We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon t…