Search Results for author:
Found 15 papers, 12 papers with code
Unleashing the Potential of Model Bias for Generalized Category Discovery
The primary challenges stem from model bias induced by pre-training on only known categories and the lack of precise supervision for novel ones, leading to category bias towards known categories and category confusion among different novel categories, which hinders models' ability to identify novel categories effectively.
VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking
Current LiDAR point cloud-based 3D single object tracking (SOT) methods typically rely on point-based representation network.
Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models
Knowledge-based Visual Question Answering (KVQA) requires both image and world knowledge to answer questions.
P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds
Moreover, under the same point-based representation, P2P-point outperforms the previous motion tracker M$^2$Track by \textbf{3. 3\%} and \textbf{6. 7\%} on the KITTI and NuScenes, while running at a considerably high speed of \textbf{107 Fps} on a single RTX3090 GPU.
Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models
In this setting, a CL learner is required to incrementally learn from multiple domains and classify test images from both seen and unseen domains without any domain-identity hint.
AGLA: Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
To this end, we propose Assembly of Global and Local Attention (AGLA), a training-free and plug-and-play approach that mitigates object hallucinations by exploring an ensemble of global features for response generation and local features for visual discrimination simultaneously.
MMRel: A Relation Understanding Benchmark in the MLLM Era
Though Multi-modal Large Language Models (MLLMs) have recently achieved significant progress, they often face various problems while handling inter-object relations, i. e., the interaction or association among distinct objects.
Color Space Learning for Cross-Color Person Re-Identification
The primary color profile of the same identity is assumed to remain consistent in typical Person Re-identification (Person ReID) tasks.
Towards Category Unification of 3D Single Object Tracking on Point Clouds
Based on this observation, we design a novel point set representation learning network inheriting transformer architecture, termed AdaFormer, which adaptively encodes the dynamically varying shape and size information from cross-category data in a unified manner.
Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining
Cross-Domain Few-Shot Segmentation (CD-FSS) poses the challenge of segmenting novel categories from a distinct domain using only limited exemplars.
Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
Such semantic misalignment circulates in pre-training, leading to inferior zero-shot performance in dense predictions due to insufficient visual concepts captured in textual representations.
OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking
By integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals and further mitigate task misalignment.
GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking Loss
Incorporating this transformer-based voting scheme into 3D RPN, a novel Siamese method dubbed GLT-T is developed for 3D single object tracking on point clouds.
GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds
Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning.
Learning Localization-aware Target Confidence for Siamese Visual Tracking
In this paper, to alleviate this misalignment, we propose a novel tracking paradigm, called SiamLA.
