Related papers: Cross-category Video Highlight Detection via Set-b…

While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object…

Advances in Generative AI have made video-level deepfake detection increasingly challenging, exposing the limitations of current detection techniques. In this paper, we present HOLA, our solution to the Video-Level Deepfake Detection track…

Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical self-supervised…

The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or…

The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning, complementary cue selection and…

Cross-media retrieval is a research hotspot in multimedia area, which aims to perform retrieval across different media types such as image and text. The performance of existing methods usually relies on labeled data for model training.…

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably…

Supervised dictionary learning (SDL) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives. The goal of SDL is to learn a…

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches…

One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many…

Data is being produced in larger quantities than ever before in human history. It's only natural to expect a rise in demand for technology that aids humans in sifting through and analyzing this inexhaustible supply of information. This need…

Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently, resulting in unsatisfying performance and limited production usage. To address this, we propose a novel…

Unsupervised video class incremental learning (uVCIL) represents an important learning paradigm for learning video information without forgetting, and without considering any data labels. Prior approaches have focused on supervised…

With the advantage of low storage cost and high retrieval efficiency, hashing techniques have recently been an emerging topic in cross-modal similarity search. As multiple modal data reflect similar semantic content, many researches aim at…

Key frame selection in video understanding presents significant challenges. Traditional top-K selection methods, which score frames independently, often fail to optimize the selection as a whole. This independent scoring frequently results…

With the prevalence of video sharing, there are increasing demands for automatic video digestion such as highlight detection. Recently, platforms with crowdsourced time-sync video comments have emerged worldwide, providing a good…

Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model…

Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos. The benchmark setup for this task is extremely challenging due to: i) the limited size of the training sets, ii) weak…

In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for…

In this paper, we test the hypothesis that interesting events in unstructured videos are inherently audiovisual. We combine deep image representations for object recognition and scene understanding with representations from an audiovisual…