Zobrazeno 1 - 10
of 145
pro vyhledávání: '"Tian, Jiandong"'
Recent years have witnessed the remarkable progress of 3D multi-modality object detection methods based on the Bird's-Eye-View (BEV) perspective. However, most of them overlook the complementary interaction and guidance between LiDAR and camera. In t
Externí odkaz:
http://arxiv.org/abs/2411.00340
Single-source domain generalization (SDG) for object detection is a challenging yet essential task as the distribution bias of the unseen domain degrades the algorithm performance significantly. However, existing methods attempt to extract domain-inv
Externí odkaz:
http://arxiv.org/abs/2405.15225
Most of 3D single object trackers (SOT) in point clouds follow the two-stream multi-stage 3D Siamese or motion tracking paradigms, which process the template and search area point clouds with two parallel branches, built on supervised point cloud bac
Externí odkaz:
http://arxiv.org/abs/2404.05960
Human-Object Interaction (HOI) detection plays a vital role in scene understanding, which aims to predict the HOI triplet in the form of . Existing methods mainly extract multi-modal features (e.g., appearance, object semantics
Externí odkaz:
http://arxiv.org/abs/2401.05676
As a prominent parameter-efficient fine-tuning technique in NLP, prompt tuning is being explored its potential in computer vision. Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an
Externí odkaz:
http://arxiv.org/abs/2312.10376
3D single object tracking remains a challenging problem due to the sparsity and incompleteness of the point clouds. Existing algorithms attempt to address the challenges in two strategies. The first strategy is to learn dense geometric features based
Externí odkaz:
http://arxiv.org/abs/2312.10608
D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
Adapting large pre-trained image models to few-shot action recognition has proven to be an effective and efficient strategy for learning robust feature extractors, which is essential for few-shot learning. Typical fine-tuning based adaptation paradig
Externí odkaz:
http://arxiv.org/abs/2312.01431
Despite the remarkable success of existing methods for few-shot segmentation, there remain two crucial challenges. First, the feature learning for novel classes is suppressed during the training on base classes in that the novel classes are always tr
Externí odkaz:
http://arxiv.org/abs/2212.01131
While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specific overfitting on base classes and sample-specific overfitting on novel
Externí odkaz:
http://arxiv.org/abs/2207.12049