Related papers: Semi-Supervised Temporal Action Detection with Pro…
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…
Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…
Point-level weakly-supervised temporal action localization (PWTAL) aims to localize actions with only a single timestamp annotation for each action instance. Existing methods tend to mine dense pseudo labels to alleviate the label sparsity,…
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…
In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train…
The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone…
Supervised learning based object detection frameworks demand plenty of laborious manual annotations, which may not be practical in real applications. Semi-supervised object detection (SSOD) can effectively leverage unlabeled data to improve…
Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e., localization of action proposals and classification of each…
Few-shot temporal action localization (TAL) methods that adapt large models via single-prompt tuning often fail to produce precise temporal boundaries. This stems from the model learning a non-discriminative mean representation of an action…
This paper focuses on Semi-Supervised Object Detection (SSOD). Knowledge Distillation (KD) has been widely used for semi-supervised image classification. However, adapting these methods for SSOD has the following obstacles. (1) The teacher…
Self-supervised learning has demonstrated remarkable capability in representation learning for skeleton-based action recognition. Existing methods mainly focus on applying global data augmentation to generate different views of the skeleton…
Semi-supervised Camouflaged Object Detection (SSCOD) aims to reduce reliance on costly pixel-level annotations by leveraging limited annotated data and abundant unlabeled data. However, existing SSCOD methods based on Teacher-Student…
Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by…
Temporal Action Detection (TAD) requires precise localization of action boundaries within long, untrimmed video sequences. While current high-performing methods achieve strong accuracy, they are often characterized by excessive parameter…
Micro-Action Recognition (MAR) aims to classify subtle human actions in video. However, annotating MAR datasets is particularly challenging due to the subtlety of actions. To this end, we introduce the setting of Semi-Supervised MAR…
Few-shot (FS) and zero-shot (ZS) learning are two different approaches for scaling temporal action detection (TAD) to new classes. The former adapts a pretrained vision model to a new task represented by as few as a single video per class,…
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to…
Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal…
Recent development of object detection mainly depends on deep learning with large-scale benchmarks. However, collecting such fully-annotated data is often difficult or expensive for real-world applications, which restricts the power of deep…
Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and…