Related papers: StructAlign: Structured Cross-Modal Alignment for …
Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated and narrated video…
Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…
Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine…
The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…
Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…
Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches leverage contrastive learning to construct a unified embedding…
Learning social media content is the basis of many real-world applications, including information retrieval and recommendation systems, among others. In contrast with previous works that focus mainly on single modal or bi-modal learning, we…
Videos are inherently multimodal. This paper studies the problem of how to fully exploit the abundant multimodal clues for improved video categorization. We introduce a hybrid deep learning framework that integrates useful clues from…
Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progress is hampered by the lack of benchmarks with rigorous,…
Click-through rate (CTR) prediction plays as a core function module in various personalized online services. The traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality, which…
Video moment retrieval (VMR) is to search for a visual temporal moment in an untrimmed raw video by a given text query description (sentence). Existing studies either start from collecting exhaustive frame-wise annotations on the temporal…
Recent advances in reasoning models have shown remarkable progress in text-based domains, but transferring those capabilities to multimodal settings, e.g., to allow reasoning over audio-visual data, still remains a challenge, in part…
Recent studies on Neural Collapse (NC) reveal that, under class-balanced conditions, the class feature means and classifier weights spontaneously align into a simplex equiangular tight frame (ETF). In long-tailed regimes, however, severe…
Most existing cross-modal language-to-video retrieval (VR) research focuses on single-modal input from video, i.e., visual representation, while the text is omnipresent in human environments and frequently critical to understand video. To…
Video-based person re-identification (ReID) in cross-view domains (for example, aerial-ground surveillance) remains an open problem because of extreme viewpoint shifts, scale disparities, and temporal inconsistencies. To address these…
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…
Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar…
Conditional random field (CRF) and Structural Support Vector Machine (Structural SVM) are two state-of-the-art methods for structured prediction which captures the interdependencies among output variables. The success of these methods is…
Building a universal Video-Language model for solving various video understanding tasks (\emph{e.g.}, text-video retrieval, video question answering) is an open challenge to the machine learning field. Towards this goal, most recent works…
Foundation Models (FMs) have been successful in various computer vision tasks like image classification, object detection and image segmentation. However, these tasks remain challenging when these models are tested on datasets with…