Related papers: Orthogonal Hyper-category Guided Multi-interest El…

Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the…

Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a…

The human visual system uses numerous cues for depth perception, including disparity, accommodation, motion parallax and occlusion. It is incumbent upon virtual-reality displays to satisfy these cues to provide an immersive user experience.…

Food image classification is essential for monitoring health and tracking dietary in image-based dietary assessment methods. However, conventional systems often rely on static datasets with fixed classes and uniform distribution. In…

As machine learning (ML) applications grow increasingly complex in recent years, modern ML frameworks often need to address multiple potentially conflicting objectives with coupled decision variables across different layers. This creates a…

Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time. To capture this intuition, we…

This thesis presents an innovative approach to automate video thumbnail selection for traditional broadcast content. Our methodology establishes stringent criteria for diverse, representative, and aesthetically pleasing thumbnails,…

Multimodal Emotion Recognition in Conversation (MERC) aims to enhance emotion understanding by integrating complementary cues from text, audio, and visual modalities. Existing MERC approaches predominantly focus on cross-modal shared…

The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…

Online microblogging services that have been increasingly used by people to share and exchange information, have emerged as a promising way to profiling multimedia contents, in a sense to provide users a socialized abstraction and…

In e-commerce ranking, implicit user feedback is systematically confounded by Position Bias -- the strong propensity of users to interact with top-ranked items regardless of relevance. While Deep Learning architectures (e.g., Two-Tower…

Modern web-based platforms show ranked lists of recommendations to users, attempting to maximise user satisfaction or business metrics. Typically, the goal of such systems boils down to maximising the exposure probability for items that are…

Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive…

Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to…

The practicality of a video surveillance system is adversely limited by the amount of queries that can be placed on human resources and their vigilance in response. To transcend this limitation, a major effort under way is to include…

Online recommender systems should be always aligned with users' current interest to accurately suggest items that each user would like. Since user interest usually evolves over time, the update strategy should be flexible to quickly catch…

Computer vision tasks are traditionally defined and evaluated using semantic categories. However, it is known to the field that semantic classes do not necessarily correspond to a unique visual class (e.g. inside and outside of a car).…

Stories can have tremendous power -- not only useful for entertainment, they can activate our interests and mobilize our actions. The degree to which a story resonates with its audience may be in part reflected in the emotional journey it…

Recommendation systems capable of providing diverse sets of results are a focus of increasing importance, with motivations ranging from fairness to novelty and other aspects of optimizing user experience. One form of diversity of recent…

Conventional recommendation systems succeed in identifying relevant content but often fail to provide users with surprising or novel items. Multimodal Large Language Models (MLLMs) possess the world knowledge and multimodal understanding…