29 citations · 148 across the 29 of their papers we have counts for
31 papers
VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding
Yucheng Liu, Yufei Yin, Mingxiao Feng +3
Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended temporal spans. Existing app…
BookNet: Book Image Rectification via Cross-Page Attention Network
Shaokai Liu, Hao Feng, Bozhi Luan +3
Book image rectification presents unique challenges due to its complex geometric distortions from binding constraints, where left and right pages exhibit distinctly asymmetric curv…
Self-Classification Enhancement and Correction for Weakly Supervised Object Detection
Yufei Yin, Lechao Cheng, Wengang Zhou +3
In recent years, weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost. The success of recent WSOD models is often ascribed to the two…
HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation
Sha Zhang, Jiajun Deng, Lei Bai +3
We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in…
DeepEraser: Deep Iterative Context Mining for Generic Text Eraser
Hao Feng, Wendi Wang, Shaokai Liu +3
In this work, we present DeepEraser, an effective deep network for generic text removal. DeepEraser utilizes a recurrent architecture that erases the text in an image via iterative…
IMD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation
Yunyao Mao, Jiajun Deng, Wengang Zhou +3
Recent progresses on self-supervised 3D human action representation learning are largely attributed to contrastive learning. However, in conventional contrastive frameworks, the ri…
Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition
Xuanyu Yi, Jiajun Deng, Qianru Sun +3
We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-trained 2D model. Surpri…
SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
Hao Feng, Wendi Wang, Jiajun Deng +3
In fisheye images, rich distinct distortion patterns are regularly distributed in the image plane. These distortion patterns are independent of the visual content and provide infor…
Masked Motion Predictors are Strong 3D Action Representation Learners
Yunyao Mao, Jiajun Deng, Wengang Zhou +3
In 3D human action recognition, limited supervised data makes it challenging to fully tap into the modeling potential of powerful networks such as transformers. As a result, resear…
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
Yufei Yin, Jiajun Deng, Wengang Zhou +2
Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement. However, with only…
Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection
Yingjie Wang, Jiajun Deng, Yao Li +6
LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocit…
Deep Unrestricted Document Image Rectification
Hao Feng, Shaokai Liu, Jiajun Deng +2
In recent years, tremendous efforts have been made on document image rectification, but existing advanced algorithms are limited to processing restricted document images, i.e., the…
Recurrent Generic Contour-based Instance Segmentation with Progressive Learning
Hao Feng, Keyi Zhou, Wengang Zhou +4
Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual objects within complex backgrounds. In this work, we prop…
OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detection
Xiaomeng Chu, Jiajun Deng, Jianmin Ji +3
The recent advance in multi-camera 3D object detection is featured by bird's-eye view (BEV) representation or object queries. However, the ill-posed transformation from image-plane…
Geometric Representation Learning for Document Image Rectification
Hao Feng, Wengang Zhou, Jiajun Deng +2
In document image rectification, there exist rich geometric constraints between the distorted image and the ground truth one. However, such geometric constraints are largely ignore…
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
Yunyao Mao, Wengang Zhou, Zhenbo Lu +2
In 3D action recognition, there exists rich complementary information between skeleton modalities. Nevertheless, how to model and utilize this information remains a challenging pro…
TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer
Jiajun Deng, Zhengyuan Yang, Daqing Liu +5
In this work, we explore neat yet effective Transformer-based frameworks for visual grounding. The previous methods generally address the core problem of visual grounding, i.e., mu…
Observing Interventions: A logic for thinking about experiments
Fausto Barbero, Katrin Schulz, Fernando R. Velázquez-Quesada +1
This paper makes a first step towards a logic of learning from experiments. For this, we investigate formal frameworks for modeling the interaction of causal and (qualitative) epis…
DocScanner: Robust Document Image Rectification with Progressive Learning
Hao Feng, Wengang Zhou, Jiajun Deng +2
Compared with flatbed scanners, portable smartphones provide more convenience for physical document digitization. However, such digitized documents are often distorted due to uncon…
DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction
Hao Feng, Yuechen Wang, Wengang Zhou +2
In this work, we propose a new framework, called Document Image Transformer (DocTr), to address the issue of geometry and illumination distortion of the document images. Specifical…
From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection
Jiajun Deng, Wengang Zhou, Yanyong Zhang +1
As an emerging data modal with precise distance sensing, LiDAR point clouds have been placed great expectations on 3D scene understanding. However, point clouds are always sparsely…
Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting
Xiaomeng Chu, Jiajun Deng, Yao Li +4
As cameras are increasingly deployed in new application domains such as autonomous driving, performing 3D object detection on monocular images becomes an important task for visual…
Weakly Supervised Temporal Adjacent Network for Language Grounding
Yuechen Wang, Jiajun Deng, Wengang Zhou +1
Temporal language grounding (TLG) is a fundamental and challenging problem for vision and language understanding. Existing methods mainly focus on fully supervised setting with tem…
Multi-Modal 3D Object Detection in Autonomous Driving: a Survey
Yingjie Wang, Qiuyu Mao, Hanqi Zhu +5
In this survey, we first introduce the background of popular sensors used for self-driving, their data properties, and the corresponding object detection algorithms. Next, we discu…