Related papers: CM2-Net: Continual Cross-Modal Mapping Network for…

Many RGB-T trackers attempt to attain robust feature representation by utilizing an adaptive weighting scheme (or attention mechanism). Different from these works, we propose a new dynamic modality-aware filter generation module (named…

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt…

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

Semantic segmentation, as a crucial component of complex visual interpretation, plays a fundamental role in autonomous vehicle vision systems. Recent studies have significantly improved the accuracy of semantic segmentation by exploiting…

Motor imitation impairments are commonly reported in individuals with autism spectrum conditions (ASCs), suggesting that motor imitation could be used as a phenotype for addressing autism heterogeneity. Traditional methods for assessing…

As wireless communication systems evolve, automatic modulation recognition (AMR) plays a key role in improving spectrum efficiency, especially in cognitive radio systems. Traditional AMR methods face challenges in complex, noisy…

In this paper, we propose a new correlated and individual multi-modal deep learning (CIMDL) method for RGB-D object recognition. Unlike most conventional RGB-D object recognition methods which extract features from the RGB and depth…

Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is key to achieve high accuracy performance on this task. Most…

Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally cheap but cannot catch temporal relationships; 3D CNNs can…

Training a neural network for a classification task typically assumes that the data to train are given from the beginning. However, in the real world, additional data accumulate gradually and the model requires additional training without…

With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the information…

Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for a wide range of applications. In this paper, we continually pre-train prevailing VFMs in a multimodal manner such that they can effortlessly process…

Inferring missing regions from severely occluded point clouds is highly challenging. Especially for 3D shapes with rich geometry and structure details, inherent ambiguities of the unknown parts are existing. Existing approaches either learn…

Multi-modal face anti-spoofing (FAS) aims to detect genuine human presence by extracting discriminative liveness cues from multiple modalities, such as RGB, infrared (IR), and depth images, to enhance the robustness of biometric…

Human behavior anomaly detection aims to identify unusual human actions, playing a crucial role in intelligent surveillance and other areas. The current mainstream methods still adopt reconstruction or future frame prediction techniques.…

Few-shot image classification remains a critical challenge in the field of computer vision, particularly in data-scarce environments. Existing methods typically rely on pre-trained visual-language models, such as CLIP. However, due to the…

Existing multimodal-based human action recognition approaches are computationally intensive, limiting their deployment in real-time applications. In this work, we present a novel and efficient pose-driven attention-guided multimodal network…

A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and…

Extracting and binding salient information from different sensory modalities to determine common features in the environment is a significant challenge in robotics. Here we present MuPNet (Multi-modal Predictive Coding Network), a…

Depth cues with affluent spatial information have been proven beneficial in boosting salient object detection (SOD), while the depth quality directly affects the subsequent SOD performance. However, it is inevitable to obtain some…