相关论文: Multi-Head Attention Driven Dynamic Visual-Semanti…

Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence. The attention mechanism in the current video captioning method learns to assign…

Systems that can find correspondences between multiple modalities, such as between speech and images, have great potential to solve different recognition and data analysis tasks in an unsupervised manner. This work studies multimodal…

Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress recently. However, previous methods primarily depend on the photometric consistency assumption, which may suffer from two limitations: indistinguishable regions…

Multi-view Stereo (MVS) aims to estimate depth and reconstruct 3D point clouds from a series of overlapping images. Recent learning-based MVS frameworks overlook the geometric information embedded in features and correlations, leading to…

We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…

Learning social media data embedding by deep models has attracted extensive research interest as well as boomed a lot of applications, such as link prediction, classification, and cross-modal search. However, for social images which contain…

Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmented views, which is a robust signal but neglects…

This paper explores the development of a multimodal sentiment analysis model that integrates text, audio, and visual data to enhance sentiment classification. The goal is to improve emotion detection by capturing the complex interactions…

Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural…

Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative information from multiple views. However, real-world multi-view datasets are often heterogeneous and imperfect, which usually…

Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…

We propose an efficient multi-view stereo (MVS) network for infering depth value from multiple RGB images. Recent studies have shown that mapping the geometric relationship in real space to neural network is an essential topic of the MVS…

Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…

Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve…

Recent text-to-image diffusion models leverage cross-attention layers, which have been effectively utilized to enhance a range of visual generative tasks. However, our understanding of cross-attention layers remains somewhat limited. In…

As bird's-eye-view (BEV) semantic segmentation is simple-to-visualize and easy-to-handle, it has been applied in autonomous driving to provide the surrounding information to downstream tasks. Inferring BEV semantic segmentation conditioned…

Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and…

With the advancement of artificial intelligence and computer vision technologies, multimodal emotion recognition has become a prominent research topic. However, existing methods face challenges such as heterogeneous data fusion and the…

With the development of medical imaging technology and machine learning, computer-assisted diagnosis which can provide impressive reference to pathologists, attracts extensive research interests. The exponential growth of medical images and…

Given a user's query, traditional image search systems rank images according to its relevance to a single modality (e.g., image content or surrounding text). Nowadays, an increasing number of images on the Internet are available with…