相关论文: Decomposed Cross-modal Distillation for RGB-based …

Multispectral pedestrian detection has gained significant attention in recent years, particularly in autonomous driving applications. To address the challenges posed by adversarial illumination conditions, the combination of thermal and…

Salient Object Detection is the task of predicting the human attended region in a given scene. Fusing depth information has been proven effective in this task. The main challenge of this problem is how to aggregate the complementary…

Recently, the RGB images and point clouds fusion methods have been proposed to jointly estimate 2D optical flow and 3D scene flow. However, as both conventional RGB cameras and LiDAR sensors adopt a frame-based data acquisition mechanism,…

Dual-arm robots have great application prospects in intelligent manufacturing due to their human-like structure when deployed with advanced intelligence algorithm. However, the previous visuomotor policy suffers from perception deficiencies…

RGB-T salient object detection (SOD) aims to segment attractive objects by combining RGB and thermal infrared images. To enhance performance, the Segment Anything Model has been fine-tuned for this task. However, the imbalance convergence…

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this…

Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was inefficient and lacked generalized representation due to the…

Multimodal learning aims to leverage information from diverse data modalities to achieve more comprehensive performance. However, conventional multimodal models often suffer from modality imbalance, where one or a few modalities dominate…

Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is crucial in many fields, including criminal analysis and psychotherapy. However,…

Non-uniform image deblurring is a challenging task due to the lack of temporal and textural information in the blurry image itself. Complementary information from auxiliary sensors such event sensors are being explored to address these…

Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion…

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…

Temporal action detection aims to recognize the action category and determine each action instance's starting and ending time in untrimmed videos. The mixed methods have achieved remarkable performance by seamlessly merging anchor-based and…

Semantic segmentation in complex environments such as urban driving scenes remains challenging under adverse lighting conditions, where RGB images alone provide insufficient information. RGB-Thermal fusion leverages the complementary…

We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images. We revise the state of art based on the RGB and depth feature fusion, where both modalities are assumed to be…

The extensive research leveraging RGB-D information has been exploited in salient object detection. However, salient visual cues appear in various scales and resolutions of RGB images due to semantic gaps at different feature levels.…

Most of existing video action recognition models ingest raw RGB frames. However, the raw video stream requires enormous storage and contains significant temporal redundancy. Video compression (e.g., H.264, MPEG-4) reduces superfluous…

Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in…

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object…

Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fusion or image…