77 citations · 403 across the 38 of their papers we have counts for
38 papers
Learning Semantic Facial Descriptors for Accurate Face Animation
Lei Zhu, Yuanqi Chen, Xiaohang Liu +2
Face animation is a challenging task. Existing model-based methods (utilizing 3DMMs or landmarks) often result in a model-like reconstruction effect, which doesn't effectively pres…
EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding
Zhiyi Pan, Guoqing Liu, Wei Gao +1
The acquisition of inductive bias through point-level contrastive learning holds paramount significance in point cloud pre-training. However, the square growth in computational req…
StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences
Shangkun Sun, Jiaming Liu, Thomas H. Li +3
Occlusions between consecutive frames have long posed a significant challenge in optical flow estimation. The inherent ambiguity introduced by occlusions directly violates the brig…
Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding
Ruyang Liu, Jingjia Huang, Wei Gao +2
Large-scale image-language pretrained models, e.g., CLIP, have demonstrated remarkable proficiency in acquiring general multi-modal knowledge through web-scale image-text data. Des…
Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
Zeshuai Deng, Zhuokun Chen, Shuaicheng Niu +3
Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. Conventional SR methods typically gather th…
FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation
Xinyu Sun, Peihao Chen, Jugang Fan +3
Learning to navigate to an image-specified goal is an important but challenging task for autonomous systems. The agent is required to reason the goal location from where a picture…
BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
Ruyang Liu, Chen Li, Yixiao Ge +3
The recent progress in Large Language Models (LLM) has spurred various advancements in image-language conversation agents, while how to build a proficient video-based dialogue syst…
Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
Peihao Chen, Xinyu Sun, Hongyan Zhi +5
We study the task of zero-shot vision-and-language navigation (ZS-VLN), a practical yet challenging problem in which an agent learns to navigate following a path described by langu…
Learning Vision-and-Language Navigation from YouTube Videos
Kunyang Lin, Peihao Chen, Diwei Huang +3
Vision-and-language navigation (VLN) requires an embodied agent to navigate in realistic 3D environments using natural language instructions. Existing VLN methods suffer from train…
Hard Sample Matters a Lot in Zero-Shot Quantization
Huantong Li, Xiangmiao Wu, Fanbing Lv +5
Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network q…
Detecting the open-world objects with the help of the Brain
Shuailei Ma, Yuefeng Wang, Ying Wei +5
Open World Object Detection (OWOD) is a novel computer vision task with a considerable challenge, bridging the gap between classic object detection (OD) benchmarks and real-world o…
LIO-PPF: Fast LiDAR-Inertial Odometry via Incremental Plane Pre-Fitting and Skeleton Tracking
Xingyu Chen, Peixi Wu, Ge Li +1
As a crucial infrastructure of intelligent mobile robots, LiDAR-Inertial odometry (LIO) provides the basic capability of state estimation by tracking LiDAR scans. The high-accuracy…
Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring
Ruyang Liu, Jingjia Huang, Ge Li +3
Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention f…
CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection
Shuailei Ma, Yuefeng Wang, Jiaqi Fan +4
Open-world object detection (OWOD), as a more general and challenging goal, requires the model trained from data on known objects to detect both known and unknown objects and incre…
Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
Peihao Chen, Dongyu Ji, Kunyang Lin +4
We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language instructions. The instructions oft…
Learning Active Camera for Multi-Object Navigation
Peihao Chen, Dongyu Ji, Kunyang Lin +5
Getting robots to navigate to multiple objects autonomously is essential yet difficult in robot applications. One of the key challenges is how to explore environments efficiently w…
Frequency-Aware Self-Supervised Monocular Depth Estimation
Xingyu Chen, Thomas H. Li, Ruonan Zhang +1
We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models. The high generalizability of our methods is achieved by solving the f…
Masked Motion Encoding for Self-Supervised Video Representation Learning
Xinyu Sun, Peihao Chen, Liangwei Chen +4
How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by pr…
Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem
Xingyu Chen, Ruonan Zhang, Ji Jiang +3
Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has larg…
Deep Geometry Post-Processing for Decompressed Point Clouds
Xiaoqing Fan, Ge Li, Dingquan Li +3
Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission. However, distortions can be introduced into the decompressed point clouds d…
Neural Texture Extraction and Distribution for Controllable Person Image Synthesis
Yurui Ren, Xiaoqing Fan, Ge Li +2
We deal with the controllable person image synthesis task which aims to re-render a human from a reference image with explicit control over body pose and appearance. Observing that…
PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering
Yurui Ren, Ge Li, Yuanqi Chen +2
Generating portrait images by controlling the motions of existing faces is an important task of great consequence to social media industries. For easy use and intuitive control, se…
Combining Attention with Flow for Person Image Synthesis
Yurui Ren, Yubo Wu, Thomas H. Li +2
Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses. In this paper, we observe that the commonly used spatial tra…
Low Pass Filter for Anti-aliasing in Temporal Action Localization
Cece Jin, Yuanqi Chen, Ge Li +2
In temporal action localization methods, temporal downsampling operations are widely used to extract proposal features, but they often lead to the aliasing problem, due to lacking…