37 citations · 113 across the 20 of their papers we have counts for
21 papers
Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Framework
Tianrui Pan, Qinglin Zhang, Chong Deng +6
Compared with half-duplex dialogue systems where the system waits for user turn completion before it responds, natural full-duplex dialogue systems require agents to act proactivel…
Towards Practical Real-Time Low-Latency Music Source Separation
Junyu Wu, Jie Liu, Tianrui Pan +2
In recent years, significant progress has been made in the field of deep learning for music demixing. However, there has been limited attention on real-time, low-latency music demi…
RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration
Jiaqi Yan, Shuning Xu, Xiangyu Chen +5
Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual reali…
In-the-wild Audio Spatialization with Flexible Text-guided Localization
Tianrui Pan, Jie Liu, Zewen Huang +2
To enhance immersive experiences, binaural audio offers spatial awareness of sounding objects in AR, VR, and embodied AI applications. While existing audio spatialization methods c…
AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection
Yuhao Chao, Jie Liu, Jie Tang +1
Industrial Anomaly Detection (IAD) poses a formidable challenge due to the scarcity of defective samples, making it imperative to deploy models capable of robust generalization to…
RASA: Replace Anyone, Say Anything -- A Training-Free Framework for Audio-Driven and Universal Portrait Video Editing
Tianrui Pan, Lin Liu, Jie Liu +4
Portrait video editing focuses on modifying specific attributes of portrait videos, guided by audio or video streams. Previous methods typically either concentrate on lip-region re…
CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution
Xin Liu, Jie Liu, Jie Tang +1
Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadra…
AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning
Yuheng Xu, Shijie Yang, Xin Liu +3
In recent years, the increasing popularity of Hi-DPI screens has driven a rising demand for high-resolution images. However, the limited computational power of edge devices poses a…
RAVSS: Robust Audio-Visual Speech Separation in Multi-Speaker Scenarios with Missing Visual Cues
Tianrui Pan, Jie Liu, Bohan Wang +2
While existing Audio-Visual Speech Separation (AVSS) methods primarily concentrate on the audio-visual fusion strategy for two-speaker separation, they demonstrate a severe perform…
GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation
Haonan Wang, Jie Liu, Jie Tang +4
In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industr…
Sketch and Refine: Towards Fast and Accurate Lane Detection
Chao Chen, Jie Liu, Chang Zhou +2
Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of…
Robust Object Modeling for Visual Tracking
Yidong Cai, Jie Liu, Jie Tang +1
Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively…
Lightweight Super-Resolution Head for Human Pose Estimation
Haonan Wang, Jie Liu, Jie Tang +1
Heatmap-based methods have become the mainstream method for pose estimation due to their superior performance. However, heatmap-based approaches suffer from significant quantizatio…
Video Frame Interpolation with Densely Queried Bilateral Correlation
Chang Zhou, Jie Liu, Jie Tang +1
Video Frame Interpolation (VFI) aims to synthesize non-existent intermediate frames between existent frames. Flow-based VFI algorithms estimate intermediate motion fields to warp t…
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution
Jie Liu, Chao Chen, Jie Tang +1
Image super-resolution (SR) serves as a fundamental tool for the processing and transmission of multimedia data. Recently, Transformer-based models have achieved competitive perfor…
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
Yawei Li, Kai Zhang, Radu Timofte +108
This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-reso…
Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution
Zongcai Du, Ding Liu, Jie Liu +3
Runtime and memory consumption are two important aspects for efficient image super-resolution (EISR) models to be deployed on resource-constrained devices. Recent advances in EISR…
AdaDM: Enabling Normalization for Image Super-Resolution
Jie Liu, Jie Tang, Gangshan Wu
Normalization like Batch Normalization (BN) is a milestone technique to normalize the distributions of intermediate layers in deep learning, enabling faster training and better gen…
Anchor-based Plain Net for Mobile Image Super-Resolution
Zongcai Du, Jie Liu, Jie Tang +1
Along with the rapid development of real-world applications, higher requirements on the accuracy and efficiency of image super-resolution (SR) are brought forward. Though existing…
Residual Feature Distillation Network for Lightweight Image Super-Resolution
Jie Liu, Jie Tang, Gangshan Wu
Recent advances in single image super-resolution (SISR) explored the power of convolutional neural network (CNN) to achieve a better performance. Despite the great success of CNN-b…
Simple and Lightweight Human Pose Estimation
Zhe Zhang, Jie Tang, Gangshan Wu
Recent research on human pose estimation has achieved significant improvement. However, most existing methods tend to pursue higher scores using complex architecture or computation…