Related papers: Action-Aware Generative Sequence Modeling for Shor…
In this paper, we address the problem of short-term action anticipation, i.e., we want to predict an upcoming action one second before it happens. We propose to harness high-level intent information to anticipate actions that will take…
People's daily lives involve numerous periodic behaviors, such as eating and traveling. Local-life platforms cater to these recurring needs by providing essential services tied to daily routines. Therefore, users' periodic intentions are…
Product recommendation can be considered as a problem in data fusion-- estimation of the joint distribution between individuals, their behaviors, and goods or services of interest. This work proposes a conditional, coupled generative…
Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…
Precise user modeling is critical for online personalized recommendation services. Generally, users' interests are diverse and are not limited to a single aspect, which is particularly evident when their behaviors are observed for a longer…
Existing video captioning methods merely provide shallow or simplistic representations of object behaviors, resulting in superficial and ambiguous descriptions. However, object behavior is dynamic and complex. To comprehensively capture the…
The increased availability and accuracy of eye-gaze tracking technology has sparked attention-related research in psychology, neuroscience, and, more recently, computer vision and artificial intelligence. The attention mechanism in…
Probabilistic models can learn users' preferences from the history of their item adoptions on a social media site, and in turn, recommend new items to users based on learned preferences. However, current models ignore psychological factors…
Inspired by recent advances in neural machine translation, that jointly align and translate using encoder-decoder networks equipped with attention, we propose an attentionbased LSTM model for human activity recognition. Our model jointly…
Egocentric action anticipation is the task of predicting the future actions a camera wearer will likely perform based on past video observations. While in a real-world system it is fundamental to output such predictions before the action…
In modern recommender systems, sequential recommendation leverages chronological user behaviors to make effective next-item suggestions, which suffers from data sparsity issues, especially for new users. One promising line of work is the…
This paper proposes a network architecture to perform variable length semantic video generation using captions. We adopt a new perspective towards video generation where we allow the captions to be combined with the long-term and short-term…
We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively…
Attentive video modeling is essential for action recognition in unconstrained videos due to their rich yet redundant information over space and time. However, introducing attention in a deep neural network for action recognition is…
Sequential fashion recommendation is of great significance in online fashion shopping, which accounts for an increasing portion of either fashion retailing or online e-commerce. The key to building an effective sequential fashion…
Recently, recommender systems have been able to emit substantially improved recommendations by leveraging user-provided reviews. Existing methods typically merge all reviews of a given user or item into a long document, and then process…
Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive adversarial post-training (AAPT) to transform a pre-trained…
Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…
Retrieving relevant observations from long multi-modal web interaction histories is challenging because relevance depends on the evolving task state, modality (screenshots, HTML text, structured signals), and temporal distance. Prior…
Deep neural networks (DNNs) have been widely employed in recommender systems including incorporating attention mechanism for performance improvement. However, most of existing attention-based models only apply item-level attention on user…