29 citations · 110 across the 30 of their papers we have counts for
18 papers · 1 filter
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
Yichao Shen, Zigang Geng, Yuhui Yuan +6
We introduce a highly performant 3D object detector for point clouds using the DETR framework. The prior attempts all end up with suboptimal results because they fail to learn accu…
DETR Doesn't Need Multi-Scale or Locality Design
Yutong Lin, Yuhui Yuan, Zheng Zhang +3
This paper presents an improved DETR detector that maintains a "plain" nature: using a single-scale feature map and global cross-attention calculations without specific locality co…
MLF-DET: Multi-Level Fusion for Cross-Modal 3D Object Detection
Zewei Lin, Yanqing Shen, Sanping Zhou +2
In this paper, we propose a novel and effective Multi-Level Fusion network, named as MLF-DET, for high-performance cross-modal 3D object DETection, which integrates both the featur…
Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization
Tao Yang, Yuwang Wang, Cuiling Lan +2
Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental ab…
MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes
Han Wang, Jiayuan Zhang, Lipeng Wan +3
Manipulation relationship detection (MRD) aims to guide the robot to grasp objects in the right order, which is important to ensure the safety and reliability of grasping in object…
Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection
Yuhao Huang, Sanping Zhou, Junjie Zhang +2
Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection. While recent grid-based detectors often encode point clouds into either voxels or pilla…
MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering
Jingjing Jiang, Nanning Zheng
Recently, finetuning pretrained Vision-Language Models (VLMs) has been a prevailing paradigm for achieving state-of-the-art performance in Visual Question Answering (VQA). However,…
BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding
Yulong Liu, Yongqiang Ma, Wei Zhou +2
Due to the lack of paired samples and the low signal-to-noise ratio of functional MRI (fMRI) signals, reconstructing perceived natural images or decoding their semantic contents fr…
Dynamic Grained Encoder for Vision Transformers
Lin Song, Songyang Zhang, Songtao Liu +5
Transformers, the de-facto standard for language modeling, have been recently applied for vision tasks. This paper introduces sparse queries for vision transformers to exploit the…
Object-fabrication Targeted Attack for Object Detection
Xuchong Zhang, Changfeng Sun, Haoliang Han +1
Recent studies have demonstrated that object detection networks are usually vulnerable to adversarial examples. Generally, adversarial attacks for object detection can be categoriz…
StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition
Yanqing Shen, Sanping Zhou, Jingwen Fu +3
Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract s…
Could Giant Pretrained Image Models Extract Universal Representations?
Yutong Lin, Ze Liu, Zheng Zhang +4
Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few pa…
Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering
Jingjing Jiang, Ziyi Liu, Nanning Zheng
Benefiting from large-scale pretrained vision language models (VLMs), the performance of visual question answering (VQA) has approached human oracles. However, finetuning such mode…
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
Jinrong Yang, Lin Song, Songtao Liu +6
Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference. These strategies are typically based on fixed and handcrafted rul…
Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization
Kun Xia, Le Wang, Sanping Zhou +2
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. W…
Social Interpretable Tree for Pedestrian Trajectory Prediction
Liushuai Shi, Le Wang, Chengjiang Long +4
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications. In this paper, we propose a tree-based method, termed as Social I…
Visual Concepts Tokenization
Tao Yang, Yuwang Wang, Yan Lu +1
Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fiel…
TransVPR: Transformer-based place recognition with multi-level attention aggregation
Ruotong Wang, Yanqing Shen, Weiliang Zuo +2
Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scen…