b'Yu-Gang Jiang'

research

∙ 06/30/2022

PolarFormer: Multi-camera 3D Object Detection with Polar Transformers

3D object detection in autonomous driving aims to reason "what" and "whe...

Yanqin Jiang, et al. ∙

research

∙ 06/07/2022

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Leveraging large-scale data can introduce performance gains on many comp...

Lingchen Meng, et al. ∙

research

∙ 04/30/2022

SVTR: Scene Text Recognition with a Single Visual Model

Dominant scene text recognition models commonly contain two building blo...

Yongkun Du, et al. ∙

research

∙ 04/26/2022

Deeper Insights into ViTs Robustness towards Common Corruptions

Recent literature have shown design strategies from Convolutions Neural ...

Rui Tian, et al. ∙

research

∙ 04/20/2022

Video Moment Retrieval from Text Queries via Single Frame Annotation

Video moment retrieval aims at finding the start and end timestamps of a...

Ran Cui, et al. ∙

research

∙ 03/28/2022

ObjectFormer for Image Manipulation Detection and Localization

Recent advances in image editing techniques have posed serious challenge...

Junke Wang, et al. ∙

research

∙ 03/15/2022

Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning

Previous few-shot learning (FSL) works mostly are limited to natural ima...

Yuqian Fu, et al. ∙

research

∙ 03/10/2022

MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes

3D dense captioning is a recently-proposed novel task, where point cloud...

Yang Jiao, et al. ∙

research

∙ 03/10/2022

Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding

Recently, one-stage visual grounders attract high attention due to the c...

Yang Jiao, et al. ∙

research

∙ 12/10/2021

Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation

Most existing vision-language pre-training methods focus on understandin...

Tianyi Liu, et al. ∙

research

∙ 12/10/2021

Cross-Modal Transferable Adversarial Attacks from Images to Videos

Recent studies have shown that adversarial examples hand-crafted on one ...

Zhipeng Wei, et al. ∙

research

∙ 11/30/2021

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition

Built on top of self-attention mechanisms, vision transformers have demo...

Lingchen Meng, et al. ∙

research

∙ 11/23/2021

Efficient Video Transformers with Spatial-Temporal Token Selection

Video transformers have achieved impressive results on major video recog...

Junke Wang, et al. ∙

research

∙ 11/22/2021

Semi-Supervised Vision Transformers

We study the training of Vision Transformers for semi-supervised image c...

Zejia Weng, et al. ∙

research

∙ 11/22/2021

CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition

The attention-based encoder-decoder framework is becoming popular in sce...

Tianlun Zheng, et al. ∙

research

∙ 10/29/2021

Attacking Video Recognition Models with Bullet-Screen Comments

Recent research has demonstrated that Deep Neural Networks (DNNs) are vu...

Kai Chen, et al. ∙

research

∙ 10/18/2021

Boosting the Transferability of Video Adversarial Examples via Temporal Translation

Although deep-learning based video recognition models have achieved rema...

Zhipeng Wei, et al. ∙

research

∙ 10/09/2021

Two-stage Visual Cues Enhancement Network for Referring Image Segmentation

Referring Image Segmentation (RIS) aims at segmenting the target object ...

Yang Jiao, et al. ∙

research

∙ 09/23/2021

Self-supervised Learning for Semi-supervised Temporal Language Grounding

Given a text description, Temporal Language Grounding (TLG) aims to loca...

Fan Luo, et al. ∙

research

∙ 09/09/2021

Towards Transferable Adversarial Attacks on Vision Transformers

Vision transformers (ViTs) have demonstrated impressive performance on a...

Zhipeng Wei, et al. ∙

research

∙ 08/18/2021

Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better

Adversarial training is one effective approach for training robust deep ...

Bojia Zi, et al. ∙

research

∙ 08/10/2021

FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting

Blind face inpainting refers to the task of reconstructing visual conten...

Junke Wang, et al. ∙

research

∙ 07/26/2021

Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data

A recent study finds that existing few-shot learning methods, trained on...

Yuqian Fu, et al. ∙

research

∙ 07/25/2021

Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos

Given a video demonstration, can we imitate the action contained in this...

Yuqian Fu, et al. ∙

research

∙ 05/06/2021

VideoLT: Large-scale Long-tailed Video Recognition

Label distributions in real-world are oftentimes long-tailed and imbalan...

Xing Zhang, et al. ∙

research

∙ 04/20/2021

M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection

The widespread dissemination of forged images generated by Deepfake tech...

Junke Wang, et al. ∙

research

∙ 04/20/2021

HMS: Hierarchical Modality Selection for Efficient Video Recognition

Videos are multimodal in nature. Conventional video recognition pipeline...

Zejia Weng, et al. ∙

research

∙ 01/18/2021

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

Deep neural networks (DNNs) have been widely adopted in different applic...

Shihao Zhao, et al. ∙

research

∙ 01/05/2021

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

In recent years, the abuse of a face swap technique called deepfake Deep...

Bojia Zi, et al. ∙

research

∙ 12/31/2020

Colonoscopy Polyp Detection: Domain Adaptation From Medical Report Images to Real-time Videos

Automatic colorectal polyp detection in colonoscopy video is a fundament...

Zhi-Qin Zhan, et al. ∙

research

∙ 10/20/2020

Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

Humans can easily recognize actions with only a few examples given, whil...

Yuqian Fu, et al. ∙

research

∙ 08/20/2020

Multi-modal Cooking Workflow Construction for Food Recipes

Understanding food recipe requires anticipating the implicit causal effe...

Liangming Pan, et al. ∙

research

∙ 07/28/2020

Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos

Automatically generating sentences to describe events and temporally loc...

Shaoxiang Chen, et al. ∙

research

∙ 06/24/2020

Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness

Evaluating the robustness of a defense model is a challenging task in ad...

Linxi Jiang, et al. ∙

research

∙ 05/26/2020

Long-Term Cloth-Changing Person Re-identification

Person re-identification (Re-ID) aims to match a target person across ca...

Xuelin Qian, et al. ∙

research

∙ 05/19/2020

Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt

Previous researches of sketches often considered sketches in pixel forma...

Hangyu Lin, et al. ∙

research

∙ 03/06/2020

Clean-Label Backdoor Attacks on Video Recognition Models

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can...

Shihao Zhao, et al. ∙

research

∙ 01/17/2020

Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition

Affective computing and cognitive theory are widely used in modern human...

Wenxuan Wang, et al. ∙

research

∙ 12/03/2019

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition

This paper presents LiteEval, a simple yet effective coarse-to-fine fram...

Zuxuan Wu, et al. ∙

research

∙ 11/21/2019

Heuristic Black-box Adversarial Attacks on Video Recognition Models

We study the problem of attacking video recognition models in the black-...

Zhipeng Wei, et al. ∙

research

∙ 04/10/2019

Black-box Adversarial Attacks on Video Recognition Models

Deep neural networks (DNNs) are known for their vulnerability to adversa...

Linxi Jiang, et al. ∙

research

∙ 12/21/2018

A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization

Emotional content is a crucial ingredient in user-generated videos. Howe...

Guoyun Tu, et al. ∙

research

∙ 11/28/2018

Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network

Sketch has been employed as an effective communicative tool to express t...

Peng Lu, et al. ∙

research

∙ 11/16/2018

Composite Binary Decomposition Networks

Binary neural networks have great resource and computing efficiency, whi...

You Qiaoben, et al. ∙

research

∙ 10/17/2018

Learning to Separate Domains in Generalized Zero-Shot and Open Set Learning: a probabilistic perspective

This paper studies the problem of domain division problem which aims to ...

HanZe Dong, et al. ∙

research

∙ 09/29/2018

Non-local NetVLAD Encoding for Video Classification

This paper describes our solution for the 2^nd YouTube-8M video understa...

Yongyi Tang, et al. ∙

research

∙ 09/25/2018

Object Detection from Scratch with Deep Supervision

We propose Deeply Supervised Object Detectors (DSOD), an object detectio...

Zhiqiang Shen, et al. ∙

research

∙ 09/19/2018

NAIS: Neural Attentive Item Similarity Model for Recommendation

Item-to-item collaborative filtering (aka. item-based CF) has been long ...

Xiangnan He, et al. ∙

research

∙ 07/26/2018

Recurrent Fusion Network for Image Captioning

Recently, much advance has been made in image captioning, and an encoder...

Wenhao Jiang, et al. ∙

research

∙ 07/23/2018

Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks

Recent studies on unsupervised image-to-image translation have made rema...

Minjun Li, et al. ∙

Yu-Gang Jiang

Featured Co-authors