b'Xin Jin'

research

∙ 05/24/2023

Collaborative World Models: An Online-Offline Transfer RL Approach

Training visual reinforcement learning (RL) models in offline datasets i...

0 Qi Wang, et al. ∙

research

∙ 05/10/2023

Fast Distributed Inference Serving for Large Language Models

Large language models (LLMs) power a new generation of interactive AI ap...

0 Bingyang Wu, et al. ∙

research

∙ 05/04/2023

Semantically Structured Image Compression via Irregular Group-Based Decoupling

Image compression techniques typically focus on compressing rectangular ...

0 Ruoyu Feng, et al. ∙

research

∙ 05/04/2023

Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts

Image coding for machines (ICM) aims to compress images to support downs...

0 Ruoyu Feng, et al. ∙

research

∙ 04/25/2023

Dynamic Video Frame Interpolation with integrated Difficulty Pre-Assessment

Video frame interpolation(VFI) has witnessed great progress in recent ye...

0 Ban Chen, et al. ∙

research

∙ 04/23/2023

An Order-Complexity Model for Aesthetic Quality Assessment of Homophony Music Performance

Although computational aesthetics evaluation has made certain achievemen...

0 Xin Jin, et al. ∙

research

∙ 04/22/2023

NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation

3D representation disentanglement aims to identify, decompose, and manip...

0 Baao Xie, et al. ∙

research

∙ 04/13/2023

Inpaint Anything: Segment Anything Meets Image Inpainting

Modern image inpainting systems, despite the significant progress, often...

0 Tao Yu, et al. ∙

research

∙ 04/13/2023

Energy-Efficient GPU Clusters Scheduling for Deep Learning

Training deep neural networks (DNNs) is a major workload in datacenters ...

0 Diandian Gu, et al. ∙

research

∙ 04/13/2023

[CLS] Token is All You Need for Zero-Shot Semantic Segmentation

In this paper, we propose an embarrassingly simple yet highly effective ...

0 Letian Wu, et al. ∙

research

∙ 03/24/2023

StereoScene: BEV-Assisted Stereo Matching Empowers 3D Semantic Scene Completion

3D semantic scene completion (SSC) is an ill-posed task that requires in...

0 Bohan Li, et al. ∙

research

∙ 03/21/2023

Understand Legal Documents with Contextualized Large Language Models

The growth of pending legal cases in populous countries, such as India, ...

0 Xin Jin, et al. ∙

research

∙ 03/13/2023

Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective

In recent years, we have witnessed the great advancement of Deep neural ...

0 Xin Li, et al. ∙

research

∙ 03/10/2023

QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression

Learned image compression has exhibited promising compression performanc...

0 Kedeng Tong, et al. ∙

research

∙ 02/25/2023

TBFormer: Two-Branch Transformer for Image Forgery Localization

Image forgery localization aims to identify forged regions by capturing ...

0 Yaqi Liu, et al. ∙

research

∙ 02/01/2023

Stable Attribute Group Editing for Reliable Few-shot Image Generation

Few-shot image generation aims to generate data of an unseen category ba...

0 Guanqi Ding, et al. ∙

research

∙ 01/26/2023

Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning

We present AIRS: Automatic Intrinsic Reward Shaping that intelligently a...

0 Mingqi Yuan, et al. ∙

research

∙ 01/14/2023

An Order-Complexity Model for Aesthetic Quality Assessment of Symbolic Homophony Music Scores

Computational aesthetics evaluation has made great achievements in the f...

0 Xin Jin, et al. ∙

research

∙ 12/06/2022

GAS-Net: Generative Artistic Style Neural Networks for Fonts

Generating new fonts is a time-consuming and labor-intensive, especially...

0 Haoyang He, et al. ∙

research

∙ 11/28/2022

Tackling Visual Control via Multi-View Exploration Maximization

We present MEM: Multi-view Exploration Maximization for tackling complex...

0 Mingqi Yuan, et al. ∙

research

∙ 11/18/2022

Task Residual for Tuning Vision-Language Models

Large-scale vision-language models (VLMs) pre-trained on billion-level d...

0 Tao Yu, et al. ∙

research

∙ 11/07/2022

A Unified Pyramid Recurrent Network for Video Frame Interpolation

Flow-guide synthesis provides a common framework for frame interpolation...

0 Xin Jin, et al. ∙

research

∙ 09/19/2022

Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning

Exploration is critical for deep reinforcement learning in complex envir...

0 Mingqi Yuan, et al. ∙

research

∙ 09/16/2022

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

In unsupervised domain adaptation (UDA), directly adapting from the sour...

3 Lin Chen, et al. ∙

research

∙ 08/31/2022

Orloj: Predictably Serving Unpredictable DNNs

Existing DNN serving solutions can provide tight latency SLOs while main...

0 Peifeng Yu, et al. ∙

research

∙ 08/22/2022

Aesthetics Driven Autonomous Time-Lapse Photography Generation by Virtual and Real Robots

Time-lapse photography is employed in movies and promotional films becau...

0 Xiaobo Gao, et al. ∙

research

∙ 08/19/2022

Hierarchical Compositional Representations for Few-shot Action Recognition

Recently action recognition has received more and more attention for its...

15 Changzhen Li, et al. ∙

research

∙ 08/14/2022

Underwater Ranker: Learn Which Is Better and How to Be Better

In this paper, we present a ranking-based underwater image quality asses...

6 Chunle Guo, et al. ∙

research

∙ 08/10/2022

Aesthetic Visual Question Answering of Photographs

Aesthetic assessment of images can be categorized into two main forms: n...

5 Xin Jin, et al. ∙

research

∙ 08/09/2022

Aesthetic Language Guidance Generation of Images Using Attribute Comparison

With the vigorous development of mobile photography technology, major mo...

0 Xin Jin, et al. ∙

research

∙ 08/09/2022

Aesthetic Attributes Assessment of Images with AMANv2 and DPC-CaptionsV2

Image aesthetic quality assessment is popular during the last decade. Be...

0 Xinghui Zhou, et al. ∙

research

∙ 08/09/2022

Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning

In recent years, image generation has made great strides in improving th...

0 Xin Jin, et al. ∙

research

∙ 07/17/2022

Learning with Recoverable Forgetting

Life-long learning aims at learning a sequence of tasks without forgetti...

0 Jingwen Ye, et al. ∙

research

∙ 07/17/2022

LambdaLite: Application-Level Optimization for Cold Start Latency in Serverless Computing

Serverless computing is an emerging cloud computing paradigm that frees ...

0 Jinfeng Wen, et al. ∙

research

∙ 07/05/2022

Image Coding for Machines with Omnipotent Feature Learning

Image Coding for Machines (ICM) aims to compress images for AI tasks ana...

0 Ruoyu Feng, et al. ∙

research

∙ 07/05/2022

Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets

With the continuous development of social software and multimedia techno...

0 Xin Jin, et al. ∙

research

∙ 06/20/2022

Short Video Uprising: How #BlackLivesMatter Content on TikTok Challenges the Protest Paradigm

This study uses TikTok (N = 8,173) to examine how short-form video platf...

0 Yanru Jiang, et al. ∙

research

∙ 06/15/2022

Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading

This paper proposes Mandheling, the first system that enables highly res...

0 Daliang Xu, et al. ∙

research

∙ 06/14/2022

Edge Security: Challenges and Issues

Edge computing is a paradigm that shifts data processing services to the...

0 Xin Jin, et al. ∙

research

∙ 04/30/2022

MiCS: Near-linear Scaling for Training Gigantic Model on Public Cloud

Existing general purpose frameworks for gigantic model training, i.e., m...

0 Zhen Zhang, et al. ∙

research

∙ 04/08/2022

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

Adversarial learning has achieved remarkable performances for unsupervis...

0 Lin Chen, et al. ∙

research

∙ 04/02/2022

Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency

In recent years, creative content generations like style transfer and ne...

0 Zhenhuan Liu, et al. ∙

research

∙ 03/16/2022

Attribute Group Editing for Reliable Few-shot Image Generation

Few-shot image generation is a challenging task even using the state-of-...

3 Guanqi Ding, et al. ∙

research

∙ 01/25/2022

Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks

Traditional media coding schemes typically encode image/video into a sem...

2 Xin Jin, et al. ∙

research

∙ 01/08/2022

Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment

In the tasks of image aesthetic quality evaluation, it is difficult to r...

10 Xin Jin, et al. ∙

research

∙ 12/26/2021

Learning Cross-Scale Prediction for Efficient Neural Video Compression

In this paper, we present the first neural video codec that can compete ...

13 Zongyu Guo, et al. ∙

research

∙ 12/16/2021

The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization

We introduce the first comprehensive 3D dataset for the task of unsuperv...

0 Paul Bergmann, et al. ∙

research

∙ 12/12/2021

Demystifying Developers' Issues in Distributed Training of Deep Learning Software

Deep learning (DL) has been pervasive in a wide spectrum of nowadays sof...

0 Diandian Gu, et al. ∙

research

∙ 12/01/2021

Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification

Existing person re-identification (ReID) methods typically directly load...

0 Zizheng Yang, et al. ∙

research

∙ 11/26/2021

Confounder Identification-free Causal Visual Feature Learning

Confounders in deep learning are in general detrimental to model's gener...

0 Xin Li, et al. ∙

Xin Jin

Featured Co-authors