Related papers: Disentangled Action Recognition with Knowledge Bas…
We propose an action parsing algorithm to parse a video sequence containing an unknown number of actions into its action segments. We argue that context information, particularly the temporal information about other actions in the video…
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 paper strives to recognize activities in the dark, as well as in the day. We first establish that state-of-the-art activity recognizers are effective during the day, but not trustworthy in the dark. The main causes are the limited…
We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras that contain a human actor along with background motion.…
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large. This makes end-to-end supervised training of a recognition system impractical as no training set is…
Video understanding is to recognize and classify different actions or activities appearing in the video. A lot of previous work, such as video captioning, has shown promising performance in producing general video understanding. However, it…
We consider the task of training a neural network to anticipate human actions in video. This task is challenging given the complexity of video data, the stochastic nature of the future, and the limited amount of annotated training data. In…
Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance…
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages…
Interactive autonomous applications require robustness of the perception engine to artifacts in unconstrained videos. In this paper, we examine the effect of camera motion on the task of action detection. We develop a novel ranking method…
Recent advances in explainable recommendations have explored the integration of language models to analyze natural language rationales for user-item interactions. Despite their potential, existing methods often rely on ID-based…
Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context. Despite recent progress, key challenges remain, including redundant cross-modal…
Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties. The task of temporal action segmentation, which aims at translating an…
Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor performance when the test data consists of videos with unseen…
We present a system that demonstrates how the compositional structure of events, in concert with the compositional structure of language, can interplay with the underlying focusing mechanisms in video action recognition, thereby providing a…
Sensory data are often comprised of independent content and transformation factors. For example, face images may have shapes as content and poses as transformation. To infer separately these factors from given data, various…
In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks…
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation. Existing methods largely rely on extensive neural language annotations to discern composable latent semantics, a process that…
Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years. Compared with static graph, the dynamic graph is a comprehensive embodiment of both the intrinsic stable characteristics of…
Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previ- ous state-of-the-art methods using hand-crafted potentials…