Related papers: Orthogonal Hyper-category Guided Multi-interest El…
Highlight detection models are typically trained to identify cues that make visual content appealing or interesting for the general public, with the objective of reducing a video to such moments. However, the "interestingness" of a video…
Recommender systems that learn from implicit feedback often use large volumes of a single type of implicit user feedback, such as clicks, to enhance the prediction of sparse target behavior such as purchases. Using multiple types of…
Collaborative filtering is a very useful general technique for exploiting the preference patterns of a group of users to predict the utility of items to a particular user. Previous research has studied several probabilistic graphic models…
We present LongVPO, a novel two-stage Direct Preference Optimization framework that enables short-context vision-language models to robustly understand ultra-long videos without any long-video annotations. In Stage 1, we synthesize…
Deep learning has proved to be very effective in video action recognition. Video violence recognition attempts to learn the human multi-dynamic behaviours in more complex scenarios. In this work, we develop a method for video violence…
Personalized recommendation stands as a ubiquitous channel for users to explore information or items aligned with their interests. Nevertheless, prevailing recommendation models predominantly rely on unique IDs and categorical features for…
Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region…
Multi-modal class-incremental learning (MMCIL) seeks to leverage multi-modal data, such as audio-visual and image-text pairs, thereby enabling models to learn continuously across a sequence of tasks while mitigating forgetting. While…
Recent advances in multimodal recommendation enable richer item understanding, while modeling users' multi-scale interests across temporal horizons has attracted growing attention. However, effectively exploiting multimodal item sequences…
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise…
It is common for people to engage in information acquisition tasks while on the move. To understand how users' visual behaviors influence microlearning, a form of mobile information acquisition, we conducted a shadowing study with 8…
Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications, whereas the data of rare fine-grained categories is very limited. Therefore, we…
Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that…
Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring…
Capturing user intent across heterogeneous behavioral domains stands as a fundamental challenge in session-based recommender systems. Yet, existing multi-domain approaches frequently fail to isolate the distinct contribution of cross-domain…
Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…
Video-text retrieval has been a crucial and fundamental task in multi-modal research. The development of video-text retrieval has been considerably promoted by large-scale multi-modal contrastive pre-training, which primarily focuses on…
Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such…
Given a sequence of sets, where each set has a timestamp and contains an arbitrary number of elements, temporal sets prediction aims to predict the elements in the subsequent set. Previous studies for temporal sets prediction mainly focus…
We present a novel approach for discovering human interactions in videos. Activity understanding techniques usually require a large number of labeled examples, which are not available in many practical cases. Here, we focus on recovering…