Related papers: Temporal Action Proposal Generation with Backgroun…
Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation.…
Trajectory prediction aims to predict the movement trend of the agents like pedestrians, bikers, vehicles. It is helpful to analyze and understand human activities in crowded spaces and widely applied in many areas such as surveillance…
Weakly supervised temporal action localization aims to detect and localize actions in untrimmed videos with only video-level labels during training. However, without frame-level annotations, it is challenging to achieve localization…
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos,…
Typical textual descriptions that accompany online videos are 'weak': i.e., they mention the main concepts in the video but not their corresponding spatio-temporal locations. The concepts in the description are typically heterogeneous…
This technical report presents our solution to the HACS Temporal Action Localization Challenge 2021, Weakly-Supervised Learning Track. The goal of weakly-supervised temporal action localization is to temporally locate and classify action of…
Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further…
Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous…
Temporal action detection (TAD) aims to identify and localize action instances in untrimmed videos, which is essential for various video understanding tasks. However, recent improvements in model performance, driven by larger feature…
The cold-start problem is a long-standing challenge in recommender systems due to the lack of user-item interactions, which significantly hurts the recommendation effect over new users and items. Recently, meta-learning based methods…
Standard RAG pipelines based on chunking excel at simple factual retrieval but fail on complex multi-hop queries due to a lack of structural connectivity. Conversely, initial strategies that interleave retrieval with reasoning often lack…
Temporal link prediction (TLP) models are commonly evaluated based on predictive accuracy, yet such evaluations do not assess whether these models capture the causal mechanisms that govern temporal interactions. In this work, we propose a…
Background subtraction has been a driving engine for many computer vision and video analytics tasks. Although its many variants exist, they all share the underlying assumption that photometric scene properties are either static or exhibit…
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects. We introduce the task of semantic…
Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ separate heads for…
The task of dynamic scene graph generation (SGG) from videos is complicated and challenging due to the inherent dynamics of a scene, temporal fluctuation of model predictions, and the long-tailed distribution of the visual relationships in…
In this work, we address the task of weakly-supervised human action segmentation in long, untrimmed videos. Recent methods have relied on expensive learning models, such as Recurrent Neural Networks (RNN) and Hidden Markov Models (HMM).…
Contextual bandit algorithms have become popular for online recommendation systems such as Digg, Yahoo! Buzz, and news recommendation in general. \emph{Offline} evaluation of the effectiveness of new algorithms in these applications is…
World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in…
Temporal networks are effective in capturing the evolving interactions of networks over time, such as social networks and e-commerce networks. In recent years, researchers have primarily concentrated on developing specific model…