53 citations · 351 across the 35 of their papers we have counts for
35 papers
Adaptive Keyframe Sampling for Long Video Understanding
Xi Tang, Jihao Qiu, Lingxi Xie +3
Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. Howev…
Depth-guided Texture Diffusion for Image Semantic Segmentation
Wei Sun, Yuan Li, Qixiang Ye +2
Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a n…
Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS
Wei Sun, Xiaosong Zhang, Fang Wan +4
Novel View Synthesis (NVS) without Structure-from-Motion (SfM) pre-processed camera poses--referred to as SfM-free methods--is crucial for promoting rapid response capabilities and…
Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussian
Wei Sun, Qi Zhang, Yanzhao Zhou +3
3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. However, achieving successful reconstruction from RGB images generally requires mul…
ChatterBox: Multi-round Multimodal Referring and Grounding
Yunjie Tian, Tianren Ma, Lingxi Xie +6
In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dia…
Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes
Di Wu, Pengfei Chen, Xuehui Yu +3
Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low ann…
Generic-to-Specific Distillation of Masked Autoencoders
Wei Huang, Zhiliang Peng, Li Dong +3
Large vision Transformers (ViTs) driven by self-supervised pre-training mechanisms achieved unprecedented progress. Lightweight ViT models limited by the model capacity, however, b…
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
Wei Sun, Chengao Liu, Linyan Zhang +6
Camouflaged objects are seamlessly blended in with their surroundings, which brings a challenging detection task in computer vision. Optimizing a convolutional neural network (CNN)…
Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration
Yunjie Tian, Lingxi Xie, Jihao Qiu +4
We propose integrally pre-trained transformer pyramid network (iTPN), towards jointly optimizing the network backbone and the neck, so that transfer gap between representation mode…
Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers
Yunjie Tian, Lingxi Xie, Jiemin Fang +6
The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual represe…
P2P-Loc: Point to Point Tiny Person Localization
Xuehui Yu, Di Wu, Qixiang Ye +2
Bounding-box annotation form has been the most frequently used method for visual object localization tasks. However, bounding-box annotation relies on a large amount of precisely a…
Exploring Complicated Search Spaces with Interleaving-Free Sampling
Yunjie Tian, Lingxi Xie, Jiemin Fang +3
The existing neural architecture search algorithms are mostly working on search spaces with short-distance connections. We argue that such designs, though safe and stable, obstacle…
Semantic-Aware Generation for Self-Supervised Visual Representation Learning
Yunjie Tian, Lingxi Xie, Xiaopeng Zhang +6
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by…
Self-supervised Feature-Gate Coupling for Dynamic Network Pruning
Mengnan Shi, Chang Liu, Jianbin Jiao +1
Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of feature…
Long-tailed Distribution Adaptation
Zhiliang Peng, Wei Huang, Zonghao Guo +3
Recognizing images with long-tailed distributions remains a challenging problem while there lacks an interpretable mechanism to solve this problem. In this study, we formulate Long…
GraFormer: Graph Convolution Transformer for 3D Pose Estimation
Weixi Zhao, Yunjie Tian, Qixiang Ye +2
Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation. To alleviate this issue, we propose GraFormer, a novel transformer…
Rethinking Sampling Strategies for Unsupervised Person Re-identification
Xumeng Han, Xuehui Yu, Guorong Li +5
Unsupervised person re-identification (re-ID) remains a challenging task. While extensive research has focused on the framework design and loss function, this paper shows that samp…
Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation
Binghao Liu, Yao Ding, Jianbin Jiao +2
Encouraging progress in few-shot semantic segmentation has been made by leveraging features learned upon base classes with sufficient training data to represent novel classes with…
Conformer: Local Features Coupling Global Representations for Visual Recognition
Zhiliang Peng, Wei Huang, Shanzhi Gu +4
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visu…
Adaptive Linear Span Network for Object Skeleton Detection
Chang Liu, Yunjie Tian, Jianbin Jiao +1
Conventional networks for object skeleton detection are usually hand-crafted. Although effective, they require intensive priori knowledge to configure representative features for o…
Prototype Mixture Models for Few-shot Semantic Segmentation
Boyu Yang, Chang Liu, Bohao Li +2
Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired direct…
Discretization-Aware Architecture Search
Yunjie Tian, Chang Liu, Lingxi Xie +2
The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods. These methods optimize a super-network with all possible edges and operation…
Vision-Dialog Navigation by Exploring Cross-modal Memory
Yi Zhu, Fengda Zhu, Zhaohuan Zhan +4
Vision-dialog navigation posed as a new holy-grail task in vision-language disciplinary targets at learning an agent endowed with the capability of constant conversation for help w…
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
Fang Wan, Chang Liu, Wei Ke +3
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detec…