Related papers: SAVE: Speech-Aware Video Representation Learning f…
State-of-the-art text-video retrieval (TVR) methods typically utilize CLIP and cosine similarity for efficient retrieval. Meanwhile, cross attention methods, which employ a transformer decoder to compute attention between each text query…
Recently, video streams have occupied a large proportion of Internet traffic, most of which contain human faces. Hence, it is necessary to predict saliency on multiple-face videos, which can provide attention cues for many content based…
This paper revisits visual representation in knowledge-based visual question answering (VQA) and demonstrates that using regional information in a better way can significantly improve the performance. While visual representation is…
This paper proposes a novel online audio-visual speaker extraction model. In the streaming regime, most studies optimize the audio network only, leaving the visual frontend less explored. We first propose a lightweight visual frontend based…
Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…
It has already been observed that audio-visual embedding is more robust than uni-modality embedding for person verification. Here, we proposed a novel audio-visual strategy that considers aggregators from a fusion perspective. First, we…
Recognizing sounds is a key aspect of computational audio scene analysis and machine perception. In this paper, we advocate that sound recognition is inherently a multi-modal audiovisual task in that it is easier to differentiate sounds…
Affective video facial analysis (AVFA) has emerged as a key research field for building emotion-aware intelligent systems, yet this field continues to suffer from limited data availability. In recent years, the self-supervised learning…
Recent progress in text-video retrieval has been largely driven by contrastive learning. However, existing methods often overlook the effect of the modality gap, which causes anchor representations to undergo in-place optimization (i.e.,…
In this paper, we propose a solution for the semi-supervised learning track (MER-SEMI) in MER2024. First, in order to enhance the performance of the feature extractor on sentiment classification tasks,we fine-tuned video and text feature…
Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research…
Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio. In AVSR, considerable efforts have been directed at datasets for facial features such as…
Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…
Video Referring Expression Comprehension (REC) aims to localize a target object in video frames referred by the natural language expression. Recently, the Transformerbased methods have greatly boosted the performance limit. However, we…
Lack of audio-video synchronization is a common problem during television broadcasts and video conferencing, leading to an unsatisfactory viewing experience. A widely accepted paradigm is to create an error detection mechanism that…
Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…
Traditional lecture videos offer flexibility but lack mechanisms for real-time clarification, forcing learners to search externally when confusion arises. Recent advances in large language models and neural avatars provide new opportunities…
Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length…
Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling missing modalities, suffering from severe performance degradation in real-world scenarios…
With the rapid advancement of sophisticated synthetic audio-visual content, e.g., for subtle malicious manipulations, ensuring the integrity of digital media has become paramount. This work presents a novel approach to temporal localization…