Related papers: Coherent Temporal Synthesis for Incremental Action…
Video behavior recognition demands stable and discriminative representations under complex spatiotemporal variations. However, prevailing data augmentation strategies for videos remain largely perturbation-driven, often introducing…
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate…
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for the problem of sound classification, in which we wish to…
The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video. Though progress has been made continuously in this field, some issues still need to be…
We propose a method for generating a temporally remapped video that matches the desired target duration while maximally preserving natural video dynamics. Our approach trains a neural network through self-supervision to recognize and…
Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly,…
Temporal action detection (TAD), which locates and recognizes action segments, remains a challenging task in video understanding due to variable segment lengths and ambiguous boundaries. Existing methods treat neighboring contexts of an…
Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is to store past experiences in the form of input examples in…
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…
Conventional replay-based approaches to continual learning (CL) require, for each learning phase with new data, the replay of samples representing all of the previously learned knowledge in order to avoid catastrophic forgetting. Since the…
Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for human video synthesis, such scheme is less reliable due to the…
Temporal Action Detection (TAD), the task of localizing and classifying actions in untrimmed video, remains challenging due to action overlaps and variable action durations. Recent findings suggest that TAD performance is dependent on the…
In this paper, we propose a method for temporal segmentation of human repetitive actions based on frequency analysis of kinematic parameters, zero-velocity crossing detection, and adaptive k-means clustering. Since the human motion data may…
Representations that can compactly and effectively capture the temporal evolution of semantic content are important to computer vision and machine learning algorithms that operate on multi-variate time-series data. We investigate such…
Text-to-Motion (T2M) generation aims to synthesize realistic human motion sequences from natural language descriptions. While two-stage frameworks leveraging discrete motion representations have advanced T2M research, they often neglect…
Scene rearrangement, like table tidying, is a challenging task in robotic manipulation due to the complexity of predicting diverse object arrangements. Web-scale trained generative models such as Stable Diffusion can aid by generating…
Time-sync comment (TSC) is a new form of user-interaction review associated with real-time video contents, which contains a user's preferences for videos and therefore well suited as the data source for video recommendations. However,…
Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is…
Sequential recommendation tasks, which aim to predict the next item a user will interact with, typically rely on models trained solely on historical data. However, in real-world scenarios, user behavior can fluctuate in the long interaction…
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works adopt a predict-and-refine strategy which converts an…