Related papers: Herding Effect based Attention for Personalized Ti…
Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…
Repeat consumption, such as repurchasing items and relistening songs, is a common scenario in daily life. To model repeat consumption, the repeat-aware recommendation has been proposed to predict which item will be re-interacted based on…
Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…
Recommender systems have achieved great success in modeling user's preferences on items and predicting the next item the user would consume. Recently, there have been many efforts to utilize time information of users' interactions with…
We study time-series classification (TSC), a fundamental task of time-series data mining. Prior work has approached TSC from two major directions: (1) similarity-based methods that classify time-series based on the nearest neighbors, and…
Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…
Chunk-based inference stands out as a popular approach in developing real-time streaming speech recognition, valued for its simplicity and efficiency. However, because it restricts the model's focus to only the history and current chunk…
Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus…
Video-based person re-identification (ReID) is challenging due to the presence of various interferences in video frames. Recent approaches handle this problem using temporal aggregation strategies. In this work, we propose a novel Context…
Modern music streaming services are heavily based on recommendation engines to serve content to users. Sequential recommendation -- continuously providing new items within a single session in a contextually coherent manner -- has been an…
With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good…
Fusion is critical for a two-stream network. In this paper, we propose a novel temporal fusion (TF) module to fuse the two-stream joints' information to predict human motion, including a temporal concatenation and a reinforcement trajectory…
Transformer-based sequential recommendation (TSR) models have shown superior performance in recommendation systems, where the quality of item representations plays a crucial role. Classical representation methods integrate item features…
Click-Through Rate (CTR) prediction, crucial in applications like recommender systems and online advertising, involves ranking items based on the likelihood of user clicks. User behavior sequence modeling has marked progress in CTR…
Micro-video recommendation aims to capture user preferences from the collaborative and context information of the interacted micro-videos, thereby predicting the appropriate videos. This target is often hindered by the inherent noise within…
Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as text to leverage Language Models (LMs) for this task has…
Text-Video Retrieval plays an important role in multi-modal understanding and has attracted increasing attention in recent years. Most existing methods focus on constructing contrastive pairs between whole videos and complete caption…
Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…
Modeling long sequences of user behaviors has emerged as a critical frontier in generative recommendation. However, existing solutions face a dilemma: linear attention mechanisms achieve efficiency at the cost of retrieval precision due to…
We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we…