相关论文: Differential Attention for Multimodal Crisis Event…

This paper focuses on the challenging crowd counting task. As large-scale variations often exist within crowd images, neither fixed-size convolution kernel of CNN nor fixed-size attention of recent vision transformers can well handle this…

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception…

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Multimodal emotion recognition (MER) aims to infer human affect by jointly modeling audio and visual cues; however, existing approaches often struggle with temporal misalignment, weakly discriminative feature representations, and suboptimal…

Weakly supervised video anomaly detection (WS-VAD) is a crucial area in computer vision for developing intelligent surveillance systems. This system uses three feature streams: RGB video, optical flow, and audio signals, where each stream…

Detecting bias in multimodal news requires models that reason over text--image pairs, not just classify text. In response, we present ViLBias, a VQA-style benchmark and framework for detecting and reasoning about bias in multimodal news.…

Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations…

In this new digital era, social media has created a severe impact on the lives of people. In recent times, fake news content on social media has become one of the major challenging problems for society. The dissemination of fabricated and…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…

Multimodal sentiment analysis has attracted increasing attention with broad application prospects. The existing methods focuses on single modality, which fails to capture the social media content for multiple modalities. Moreover, in…

Crash detection from video feeds is a critical problem in intelligent transportation systems. Recent developments in large language models (LLMs) and vision-language models (VLMs) have transformed how we process, reason about, and summarize…

Learning discriminative representations for subtle localized details plays a significant role in Fine-grained Visual Categorization (FGVC). Compared to previous attention-based works, our work does not explicitly define or localize the part…

Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatically accurate but inconsistent with visual inputs. In this…

Soft attention is a critical mechanism powering LLMs to locate relevant parts within a given context. However, individual attention weights are determined by the similarity of only a single query and key token vector. This "single token…

Timely interpretation of satellite imagery is critical for disaster response, yet existing vision-language benchmarks for remote sensing largely focus on coarse labels and image-level recognition, overlooking the functional understanding…

Social media has a significant impact on people's lives. Hate speech on social media has emerged as one of society's most serious issues in recent years. Text and pictures are two forms of multimodal data that are distributed within…

Recently, while large language models (LLMs) have demonstrated impressive results, they still suffer from hallucination, i.e., the generation of false information. Model editing is the task of fixing factual mistakes in LLMs; yet, most…

Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels. Among these approaches, multimodal violence detection, which integrates modalities such as…

Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing…

Emotion represents an essential aspect of human speech that is manifested in speech prosody. Speech, visual, and textual cues are complementary in human communication. In this paper, we study a hybrid fusion method, referred to as…