Related papers: Embarrassingly Simple Model for Early Action Propo…
Deep Candidate Generation plays an important role in large-scale recommender systems. It takes user history behaviors as inputs and learns user and item latent embeddings for candidate generation. In the literature, conventional methods…
Recently, video-based action recognition methods using convolutional neural networks (CNNs) achieve remarkable recognition performance. However, there is still lack of understanding about the generalization mechanism of action recognition…
Most of human actions consist of complex temporal compositions of more simple actions. Action recognition tasks usually relies on complex handcrafted structures as features to represent the human action model. Convolutional Neural Nets…
Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been…
This paper strives to localize the temporal extent of an action in a long untrimmed video. Where existing work leverages many examples with their start, their ending, and/or the class of the action during training time, we propose few-shot…
The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query. Most of the existing approaches rely on segment-sentence pairs (temporal annotations) for…
While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long,…
Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…
This paper considers the problem of localizing actions in videos as a sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall with few…
Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data. In this paper, a novel video based action recognition framework utilizing complementary cues is proposed to handle…
In this paper, a new video classification methodology is proposed which can be applied in both first and third person videos. The main idea behind the proposed strategy is to capture complementary information of appearance and motion…
We propose a simple but effective method to recommend exercises with high quality and diversity for students. Our method is made up of three key components: (1) candidate generation module; (2) diversity-promoting module; and (3) scope…
With the explosion of video content on the Internet, there is a need for research on methods for video analysis which take human cognition into account. One such cognitive measure is memorability, or the ability to recall visual content…
We introduce Activity Graph Transformer, an end-to-end learnable model for temporal action localization, that receives a video as input and directly predicts a set of action instances that appear in the video. Detecting and localizing…
In recent years multi-label, multi-class video action recognition has gained significant popularity. While reasoning over temporally connected atomic actions is mundane for intelligent species, standard artificial neural networks (ANN)…
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…
Given $k$ pre-trained classifiers and a stream of unlabeled data examples, how can we actively decide when to query a label so that we can distinguish the best model from the rest while making a small number of queries? Answering this…
Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of…
This paper proposes a novel generative video compression framework that leverages motion pattern priors, derived from subtle dynamics in common scenes (e.g., swaying flowers or a boat drifting on water), rather than relying on video content…
Current state-of-the-art methods solve spatiotemporal action localisation by extending 2D anchors to 3D-cuboid proposals on stacks of frames, to generate sets of temporally connected bounding boxes called \textit{action micro-tubes}.…