3 accepted papers
Diffusion-based planners have emerged as a promising approach for human-like trajectory generation in autonomous driving. Recent works incorporate reinforcement fine-tuning to enhance the robustness of diffusion planners through reward-oriented optimization in a generation-evaluation loop. However,
Cross-modal retrieval aims to bridge the semantic gap between different modalities, such as visual and textual data, enabling accurate retrieval across them. Despite significant advancements with models like CLIP that align cross-modal representations, a persistent challenge remains: the hubness pro…
Channel-spatial attention mechanisms have been extensively investigated in computer vision. However, it is still a difficult problem that how to efficiently utilize global and local contextual information laid in a feature tensor to generate an accurate 3D attention map. This paper proposes a novel…