418 citations · 1.1k across the 26 of their papers we have counts for
28 papers
RELO: Reinforcement Learning to Localize for Visual Object Tracking
Xin Chen, Chuanyu Sun, Jiao Xu +4
Conventional visual object trackers localize targets using handcrafted spatial priors, often in the form of heatmaps. Such priors provide only surrogate supervision and are poorly…
Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking
Ben Kang, Xin Chen, Dong Wang +2
Transformer-based visual trackers have demonstrated significant progress owing to their superior modeling capabilities. However, existing trackers are hampered by low speed, limiti…
ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation
Yasheng Sun, Yifan Yang, Houwen Peng +5
While language-guided image manipulation has made remarkable progress, the challenge of how to instruct the manipulation process faithfully reflecting human intentions persists. An…
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention
Xinyu Liu, Houwen Peng, Ningxin Zheng +3
Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them…
Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
Xin Chen, Ben Kang, Jiawen Zhu +3
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts…
Attentive Mask CLIP
Yifan Yang, Weiquan Huang, Yixuan Wei +8
Image token removal is an efficient augmentation strategy for reducing the cost of computing image features. However, this efficient augmentation strategy has been found to adverse…
Expanding Language-Image Pretrained Models for General Video Recognition
Bolin Ni, Houwen Peng, Minghao Chen +5
Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalizat…
TinyViT: Fast Pretraining Distillation for Small Vision Transformers
Kan Wu, Jinnian Zhang, Houwen Peng +4
Vision transformer (ViT) recently has drawn great attention in computer vision due to its remarkable model capability. However, most prevailing ViT models suffer from huge number o…
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
Guocheng Qian, Yuchen Li, Houwen Peng +4
PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such…
MiniViT: Compressing Vision Transformers with Weight Multiplexing
Jinnian Zhang, Houwen Peng, Kan Wu +4
Vision Transformer (ViT) models have recently drawn much attention in computer vision due to their high model capability. However, ViT models suffer from huge number of parameters,…
Searching the Search Space of Vision Transformer
Minghao Chen, Kan Wu, Bolin Ni +5
Vision Transformer has shown great visual representation power in substantial vision tasks such as recognition and detection, and thus been attracting fast-growing efforts on manua…
Learning to Track Objects from Unlabeled Videos
Jilai Zheng, Chao Ma, Houwen Peng +1
In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. We identify that three major challenges, i.e., moving object discovery, rich temporal…
Rethinking and Improving Relative Position Encoding for Vision Transformer
Kan Wu, Houwen Peng, Minghao Chen +2
Relative position encoding (RPE) is important for transformer to capture sequence ordering of input tokens. General efficacy has been proven in natural language processing. However…
AutoFormer: Searching Transformers for Visual Recognition
Minghao Chen, Houwen Peng, Jianlong Fu +1
Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is chal…
Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training
Hongwei Xue, Yupan Huang, Bei Liu +4
Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dom…
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Bin Yan, Houwen Peng, Kan Wu +3
Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployment…
One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
Minghao Chen, Houwen Peng, Jianlong Fu +1
Despite remarkable progress achieved, most neural architecture search (NAS) methods focus on searching for one single accurate and robust architecture. To further build models with…
Learning Spatio-Temporal Transformer for Visual Tracking
Bin Yan, Houwen Peng, Jianlong Fu +2
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies b…
Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language
Songyang Zhang, Houwen Peng, Jianlong Fu +2
We address the problem of retrieving a specific moment from an untrimmed video by natural language. It is a challenging problem because a target moment may take place in the contex…
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
Houwen Peng, Hao Du, Hongyuan Yu +3
One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across…
Towards Accurate Pixel-wise Object Tracking by Attention Retrieval
Zhipeng Zhang, Bing Li, Weiming Hu +1
The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capabl…
Revisiting Anchor Mechanisms for Temporal Action Localization
Le Yang, Houwen Peng, Dingwen Zhang +2
Most of the current action localization methods follow an anchor-based pipeline: depicting action instances by pre-defined anchors, learning to select the anchors closest to the gr…
Ocean: Object-aware Anchor-free Tracking
Zhipeng Zhang, Houwen Peng, Jianlong Fu +2
Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying…
Cyclic Differentiable Architecture Search
Hongyuan Yu, Houwen Peng, Yan Huang +4
Differentiable ARchiTecture Search, i.e., DARTS, has drawn great attention in neural architecture search. It tries to find the optimal architecture in a shallow search network and…