110 citations · 584 across the 45 of their papers we have counts for
46 papers
Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation
Quan Tang, Bowen Zhang, Jiajun Liu +2
Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction ta…
BHSD: A 3D Multi-Class Brain Hemorrhage Segmentation Dataset
Biao Wu, Yutong Xie, Zeyu Zhang +6
Intracranial hemorrhage (ICH) is a pathological condition characterized by bleeding inside the skull or brain, which can be attributed to various factors. Identifying, localizing a…
Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection
Bingqing Zhang, Sen Wang, Yifan Liu +3
Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame.…
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning
Muzhi Zhu, Hengtao Li, Hao Chen +5
Current closed-set instance segmentation models rely on pre-defined class labels for each mask during training and evaluation, largely limiting their ability to detect novel object…
Category Feature Transformer for Semantic Segmentation
Quan Tang, Chuanjian Liu, Fagui Liu +5
Aggregation of multi-stage features has been revealed to play a significant role in semantic segmentation. Unlike previous methods employing point-wise summation or concatenation f…
CTVIS: Consistent Training for Online Video Instance Segmentation
Kaining Ying, Qing Zhong, Weian Mao +7
The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS). Instance embedding learning is direc…
A Dynamic Feature Interaction Framework for Multi-task Visual Perception
Yuling Xi, Hao Chen, Ning Wang +4
Multi-task visual perception has a wide range of applications in scene understanding such as autonomous driving. In this work, we devise an efficient unified framework to solve mul…
BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation
Liyang Liu, Zihan Wang, Minh Hieu Phan +3
Current knowledge distillation approaches in semantic segmentation tend to adopt a holistic approach that treats all spatial locations equally. However, for dense prediction, stude…
SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
Bowen Zhang, Liyang Liu, Minh Hieu Phan +3
This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \textbf{SegViTv2}. In this s…
Retrieval-Enhanced Visual Prompt Learning for Few-shot Classification
Jintao Rong, Hao Chen, Linlin Ou +3
The Contrastive Language-Image Pretraining (CLIP) model has been widely used in various downstream vision tasks. The few-shot learning paradigm has been widely adopted to augment i…
Segment Anything in High Quality
Lei Ke, Mingqiao Ye, Martin Danelljan +4
The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being…
Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning
Sen Zhao, Wei Wei, Yifan Liu +6
Conversational recommendation systems (CRS) aim to timely and proactively acquire user dynamic preferred attributes through conversations for item recommendation. In each turn of C…
Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
Caiyuan Chu, Ya Li, Yifan Liu +4
Intent recognition is critical for task-oriented dialogue systems. However, for emerging domains and new services, it is difficult to accurately identify the key intent of a conver…
The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge
Xiangyu Li, Gongning Luo, Kuanquan Wang +31
Automatic intracranial hemorrhage segmentation in 3D non-contrast head CT (NCCT) scans is significant in clinical practice. Existing hemorrhage segmentation methods usually ignores…
ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Ziqin Zhou, Bowen Zhang, Yinjie Lei +2
Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. The general idea is to first generate class-agnostic region proposals and then feed…
Prior-enhanced Temporal Action Localization using Subject-aware Spatial Attention
Yifan Liu, Youbao Tang, Ning Zhang +2
Temporal action localization (TAL) aims to detect the boundary and identify the class of each action instance in a long untrimmed video. Current approaches treat video frames homog…
SegViT: Semantic Segmentation with Plain Vision Transformers
Bowen Zhang, Zhi Tian, Quan Tang +4
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level…
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
Wei Yin, Jianming Zhang, Oliver Wang +4
Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth pred…
FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation
Jianlong Yuan, Qian Qi, Fei Du +3
In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of traini…
Improving Personality Consistency in Conversation by Persona Extending
Yifan Liu, Wei Wei, Jiayi Liu +3
Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate respon…
Semi-supervised Semantic Segmentation with Mutual Knowledge Distillation
Jianlong Yuan, Jinchao Ge, Zhibin Wang +1
Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a n…
Semantic-guided Multi-Mask Image Harmonization
Xuqian Ren, Yifan Liu
Previous harmonization methods focus on adjusting one inharmonious region in an image based on an input mask. They may face problems when dealing with different perturbations on di…
Controllable Shadow Generation Using Pixel Height Maps
Yichen Sheng, Yifan Liu, Jianming Zhang +6
Shadows are essential for realistic image compositing. Physics-based shadow rendering methods require 3D geometries, which are not always available. Deep learning-based shadow synt…
Efficient Video Segmentation Models with Per-frame Inference
Yifan Liu, Chunhua Shen, Changqian Yu +1
Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods t…