Related papers: Multimodal Imbalance-Aware Gradient Modulation for…

Audio-visual deepfake detection scrutinizes manipulations in public video using complementary multimodal cues. Current methods, which train on fused multimodal data for multimodal targets face challenges due to uncertainties and…

Learning multi-modal representations is an essential step towards real-world robotic applications, and various multi-modal fusion models have been developed for this purpose. However, we observe that existing models, whose objectives are…

Weakly-Supervised Semantic Segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, current WSSS methods…

Multimodal fusion is susceptible to modality imbalance, where dominant modalities overshadow weak ones, easily leading to biased learning and suboptimal fusion, especially for incomplete modality conditions. To address this problem, we…

Unsupervised feature learning methods have proven effective for classification tasks based on a single modality. We present multimodal sparse coding for learning feature representations shared across multiple modalities. The shared…

Action quality assessment (AQA) is to assess how well an action is performed. Previous works perform modelling by only the use of visual information, ignoring audio information. We argue that although AQA is highly dependent on visual…

We investigated visual reasoning limitations of both multimodal large language models (MLLMs) and image generation models (IGMs) by creating a novel benchmark to systematically compare failure modes across image-to-text and text-to-image…

Fine-grained visual categorization (FGVC) is to categorize objects into subordinate classes instead of basic classes. One major challenge in FGVC is the co-occurrence of two issues: 1) many subordinate classes are highly correlated and are…

Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations. However, existing MML methods often optimize a uniform objective for different modalities, leading to…

Multimodal Large Models (MLLMs) have achieved remarkable progress in vision-language understanding and generation tasks. However, existing MLLMs typically rely on static modality fusion strategies, which treat all modalities equally…

In the context of Audio Visual Question Answering (AVQA) tasks, the audio visual modalities could be learnt on three levels: 1) Spatial, 2) Temporal, and 3) Semantic. Existing AVQA methods suffer from two major shortcomings; the…

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

Multimodal Sentiment Analysis (MSA) aims to identify speakers' sentiment tendencies in multimodal video content, raising serious concerns about privacy risks associated with multimodal data, such as voiceprints and facial images. Recent…

Traditional multimodal methods often assume static modality quality, which limits their adaptability in dynamic real-world scenarios. Thus, dynamical multimodal methods are proposed to assess modality quality and adjust their contribution…

Many tasks in video analysis and understanding boil down to the need for frame-based feature learning, aiming to encapsulate the relevant visual content so as to enable simpler and easier subsequent processing. While supervised strategies…

The goal of video anomaly detection is tantamount to performing spatio-temporal localization of abnormal events in the video. The multiscale temporal dependencies, visual-semantic heterogeneity, and the scarcity of labeled data exhibited by…

Weakly supervised learning has emerged as an appealing alternative to alleviate the need for large labeled datasets in semantic segmentation. Most current approaches exploit class activation maps (CAMs), which can be generated from…

With the rapid growth in deepfake video content, we require improved and generalizable methods to detect them. Most existing detection methods either use uni-modal cues or rely on supervised training to capture the dissonance between the…

Multimodal emotion recognition has recently gained much attention since it can leverage diverse and complementary relationships over multiple modalities (e.g., audio, visual, biosignals, etc.), and can provide some robustness to noisy…

The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive the dynamic scene, which is significant and imperative in many vision tasks. Most of existing methods only consider visual cues, while…