b'Jingkuan Song'

research

∙ 09/14/2023

DePT: Decoupled Prompt Tuning

This work breaks through the Base-New Tradeoff (BNT)dilemma in prompt tu...

0 Ji Zhang, et al. ∙

research

∙ 08/29/2023

MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection

Unsupervised anomaly detection (UAD) attracts a lot of research interest...

0 Yixuan Zhou, et al. ∙

research

∙ 08/23/2023

CIParsing: Unifying Causality Properties into Multiple Human Parsing

Existing methods of multiple human parsing (MHP) apply statistical model...

0 Xiaojia Chen, et al. ∙

research

∙ 08/20/2023

From Global to Local: Multi-scale Out-of-distribution Detection

Out-of-distribution (OOD) detection aims to detect "unknown" data whose ...

0 Ji Zhang, et al. ∙

research

∙ 08/10/2023

Informative Scene Graph Generation via Debiasing

Scene graph generation aims to detect visual relationship triplets, (sub...

0 Lianli Gao, et al. ∙

research

∙ 08/07/2023

Part-Aware Transformer for Generalizable Person Re-identification

Domain generalization person re-identification (DG-ReID) aims to train a...

0 Hao Ni, et al. ∙

research

∙ 05/17/2023

CageViT: Convolutional Activation Guided Efficient Vision Transformer

Recently, Transformers have emerged as the go-to architecture for both v...

0 Hao Zheng, et al. ∙

research

∙ 03/13/2023

Prototype-based Embedding Network for Scene Graph Generation

Current Scene Graph Generation (SGG) methods explore contextual informat...

4 Chaofan Zheng, et al. ∙

research

∙ 03/11/2023

DETA: Denoised Task Adaptation for Few-Shot Learning

Test-time task adaptation in few-shot learning aims to adapt a pre-train...

0 Ji Zhang, et al. ∙

research

∙ 03/10/2023

Boosting Adversarial Attacks by Leveraging Decision Boundary Information

Due to the gap between a substitute model and a victim model, the gradie...

0 Boheng Zeng, et al. ∙

research

∙ 01/28/2023

A Closer Look at Few-shot Classification Again

Few-shot classification consists of a training phase where a model is le...

0 Xu Luo, et al. ∙

research

∙ 12/17/2022

Hyperbolic Hierarchical Contrastive Hashing

Hierarchical semantic structures, naturally existing in real-world datas...

0 Rukai Wei, et al. ∙

research

∙ 11/17/2022

Progressive Tree-Structured Prototype Network for End-to-End Image Captioning

Studies of image captioning are shifting towards a trend of a fully end-...

0 Pengpeng Zeng, et al. ∙

research

∙ 10/12/2022

A Lower Bound of Hash Codes' Performance

As a crucial approach for compact representation learning, hashing has a...

0 Xiaosu Zhu, et al. ∙

research

∙ 10/05/2022

Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks

Unrestricted color attacks, which manipulate semantically meaningful col...

0 Shengming Yuan, et al. ∙

research

∙ 08/27/2022

RepParser: End-to-End Multiple Human Parsing with Representative Parts

Existing methods of multiple human parsing usually adopt a two-stage str...

3 Xiaojia Chen, et al. ∙

research

∙ 08/17/2022

Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning

Scene graph generation (SGG) is a fundamental task aimed at detecting vi...

6 Tao He, et al. ∙

research

∙ 07/12/2022

Frequency Domain Model Augmentation for Adversarial Attack

For black-box attacks, the gap between the substitute model and the vict...

16 Yuyang Long, et al. ∙

research

∙ 07/11/2022

Adaptive Fine-Grained Predicates Learning for Scene Graph Generation

The performance of current Scene Graph Generation (SGG) models is severe...

0 Xinyu Lyu, et al. ∙

research

∙ 06/30/2022

Skeleton-based Action Recognition via Adaptive Cross-Form Learning

Skeleton-based action recognition aims to project skeleton sequences to ...

0 Xuanhan Wang, et al. ∙

research

∙ 06/23/2022

Learning To Generate Scene Graph from Head to Tail

Scene Graph Generation (SGG) represents objects and their interactions w...

0 Chaofan Zheng, et al. ∙

research

∙ 06/21/2022

KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing

Part-level attribute parsing is a fundamental but challenging task, whic...

0 Xuanhan Wang, et al. ∙

research

∙ 06/21/2022

KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences

Human densepose estimation, aiming at establishing dense correspondences...

0 Xuanhan Wang, et al. ∙

research

∙ 06/04/2022

From Pixels to Objects: Cubic Visual Attention for Visual Question Answering

Recently, attention-based Visual Question Answering (VQA) has achieved g...

0 Jingkuan Song, et al. ∙

research

∙ 06/02/2022

Structured Two-stream Attention Network for Video Question Answering

To date, visual question answering (VQA) (i.e., image QA and video QA) i...

0 Lianli Gao, et al. ∙

research

∙ 05/19/2022

Support-set based Multi-modal Representation Enhancement for Video Captioning

Video captioning is a challenging task that necessitates a thorough comp...

0 Xiaoya Chen, et al. ∙

research

∙ 04/06/2022

Fine-Grained Predicates Learning for Scene Graph Generation

The performance of current Scene Graph Generation models is severely ham...

0 Xinyu Lyu, et al. ∙

research

∙ 03/21/2022

Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

Modeling latent variables with priors and hyperpriors is an essential pr...

4 Xiaosu Zhu, et al. ∙

research

∙ 03/10/2022

Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack

Defense models against adversarial attacks have grown significantly, but...

0 Ye Liu, et al. ∙

research

∙ 03/09/2022

Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation

In recent years, the adversarial vulnerability of deep neural networks (...

1 Qilong Zhang, et al. ∙

research

∙ 02/22/2022

Relation Regularized Scene Graph Generation

Scene graph generation (SGG) is built on top of detected objects to pred...

0 Yuyu Guo, et al. ∙

research

∙ 02/22/2022

One-shot Scene Graph Generation

As a structured representation of the image content, the visual scene gr...

0 Yuyu Guo, et al. ∙

research

∙ 11/05/2021

Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing

Part-level Action Parsing aims at part state parsing for boosting action...

0 Xuanhan Wang, et al. ∙

research

∙ 10/25/2021

Fast Gradient Non-sign Methods

Adversarial attacks make their success in fooling DNNs and among them, g...

0 Yaya Cheng, et al. ∙

research

∙ 08/30/2021

From General to Specific: Informative Scene Graph Generation via Balance Adjustment

The scene graph generation (SGG) task aims to detect visual relationship...

2 Yuyu Guo, et al. ∙

research

∙ 08/20/2021

Unsupervised Domain-adaptive Hash for Networks

Abundant real-world data can be naturally represented by large-scale net...

17 Tao He, et al. ∙

research

∙ 08/20/2021

Semi-supervised Network Embedding with Differentiable Deep Quantisation

Learning accurate low-dimensional embeddings for a network is a crucial ...

3 Tao He, et al. ∙

research

∙ 08/19/2021

Semantic Compositional Learning for Low-shot Scene Graph Generation

Scene graphs provide valuable information to many downstream tasks. Many...

6 Tao He, et al. ∙

research

∙ 08/19/2021

Exploiting Scene Graphs for Human-Object Interaction Detection

Human-Object Interaction (HOI) detection is a fundamental visual task ai...

15 Tao He, et al. ∙

research

∙ 05/25/2021

Feature Space Targeted Attacks by Statistic Alignment

By adding human-imperceptible perturbations to images, DNNs can be easil...

0 Lianli Gao, et al. ∙

research

∙ 04/20/2021

Staircase Sign Method for Boosting Adversarial Attacks

Crafting adversarial examples for the transfer-based attack is challengi...

0 Lianli Gao, et al. ∙

research

∙ 12/31/2020

Patch-wise++ Perturbation for Adversarial Targeted Attacks

Although great progress has been made on adversarial attacks for deep ne...

14 Lianli Gao, et al. ∙

research

∙ 07/14/2020

Patch-wise Attack for Fooling Deep Neural Network

By adding human-imperceptible noise to clean images, the resultant adver...

12 Lianli Gao, et al. ∙

research

∙ 06/13/2020

Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation

Despite the huge progress in scene graph generation in recent years, its...

0 Tao He, et al. ∙

research

∙ 03/31/2020

Binary Neural Networks: A Survey

The binary neural network, largely saving the storage and computation, s...

22 Haotong Qin, et al. ∙

research

∙ 09/24/2019

IR-Net: Forward and Backward Information Retention for Highly Accurate Binary Neural Networks

Weight and activation binarization is an effective approach to deep neur...

1 Haotong Qin, et al. ∙

research

∙ 08/12/2019

Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking

A major challenge in matching images and text is that they have intrinsi...

8 Tan Wang, et al. ∙

research

∙ 07/01/2019

One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network

With the recent explosive increase of digital data, image recognition an...

0 Tao He, et al. ∙

research

∙ 06/28/2019

Localizing Unseen Activities in Video via Image Query

Action localization in untrimmed videos is an important topic in the fie...

1 Zhu Zhang, et al. ∙

research

∙ 06/28/2019

Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks

Open-ended video question answering aims to automatically generate the n...

1 Zhu Zhang, et al. ∙

Jingkuan Song

Featured Co-authors