115 citations · 502 across the 24 of their papers we have counts for
24 papers
GeoWorldAD: Geometry World Action Model for Autonomous Driving
Songyan Zhang, Jinyuan Tian, Hanbing Li +9
Autonomous driving requires both safe and efficient planning decisions in dynamic 3D environments. Although recent Vision/Video-Action models learn policies directly from visual ob…
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Ziyang Yao, Haochen Liu, Yuncheng Jiang +10
Autonomous driving requires reasoning about how ego actions shape future world evolution, rather than merely mapping observations to actions. However, most end-to-end methods rely…
Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Jinghui Lu, Jiayi Guan, Zhijian Huang +47
Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is…
SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
Lizhe Liu, Bohua Wang, Hongwei Xie +5
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems. Recently, object-free methods have attracted considerable attention. Such…
UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
Mingjie Pan, Li Liu, Jiaming Liu +6
In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023. Existing…
Learning cross space mapping via DNN using large scale click-through logs
Wei Yu, Kuiyuan Yang, Yalong Bai +2
The gap between low-level visual signals and high-level semantics has been progressively bridged by continuous development of deep neural network (DNN). With recent progress of DNN…
SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow
Xiangtai Li, Jiangning Zhang, Yibo Yang +4
In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feat…
Global Aggregation then Local Distribution for Scene Parsing
Xiangtai Li, Li Zhang, Guangliang Cheng +4
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherentl…
Improving Video Instance Segmentation via Temporal Pyramid Routing
Xiangtai Li, Hao He, Yibo Yang +5
Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment, and track each instance in a video sequence. Existing approaches are ma…
BoundarySqueeze: Image Segmentation as Boundary Squeezing
Hao He, Xiangtai Li, Yibo Yang +5
This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing…
Towards Efficient Scene Understanding via Squeeze Reasoning
Xiangtai Li, Xia Li, Ansheng You +5
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, i…
Feature-metric Loss for Self-supervised Learning of Depth and Egomotion
Chang Shu, Kun Yu, Zhixiang Duan +1
Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimi…
Semantic Flow for Fast and Accurate Scene Parsing
Xiangtai Li, Ansheng You, Zhen Zhu +4
In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps wi…
Global Aggregation then Local Distribution in Fully Convolutional Networks
Xiangtai Li, Li Zhang, Ansheng You +3
It has been widely proven that modelling long-range dependencies in fully convolutional networks (FCNs) via global aggregation modules is critical for complex scene understanding t…
Dual Graph Convolutional Network for Semantic Segmentation
Li Zhang, Xiangtai Li, Anurag Arnab +3
Exploiting long-range contextual information is key for pixel-wise prediction tasks such as semantic segmentation. In contrast to previous work that uses multi-scale feature fusion…
Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
Youmin Zhang, Yimin Chen, Xiao Bai +4
State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and…
GFF: Gated Fully Fusion for Semantic Segmentation
Xiangtai Li, Houlong Zhao, Lei Han +2
Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Net…
Automatic Dataset Augmentation
Yalong Bai, Kuiyuan Yang, Tao Mei +2
Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent year…
Feature Incay for Representation Regularization
Yuhui Yuan, Kuiyuan Yang, Chao Zhang
Softmax loss is widely used in deep neural networks for multi-class classification, where each class is represented by a weight vector, a sample is represented as a feature vector,…
Hard-Aware Deeply Cascaded Embedding
Yuhui Yuan, Kuiyuan Yang, Chao Zhang
Riding on the waves of deep neural networks, deep metric learning has also achieved promising results in various tasks using triplet network or Siamese network. Though the basic go…
Visualizing and Comparing Convolutional Neural Networks
Wei Yu, Kuiyuan Yang, Yalong Bai +2
Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexi…
The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
Tianjun Xiao, Yichong Xu, Kuiyuan Yang +3
Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the p…
Scale-Invariant Convolutional Neural Networks
Yichong Xu, Tianjun Xiao, Jiaxing Zhang +2
Even though convolutional neural networks (CNN) has achieved near-human performance in various computer vision tasks, its ability to tolerate scale variations is limited. The popul…
Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data
Yalong Bai, Kuiyuan Yang, Wei Yu +2
Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-…