Related papers: I Have Seen Enough: A Teacher Student Network for …

Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a…

This paper presents a novel approach for temporal and semantic segmentation of edited videos into meaningful segments, from the point of view of the storytelling structure. The objective is to decompose a long video into more manageable…

Video text spotting is still an important research topic due to its various real-applications. Previous approaches usually fall into the four-staged pipeline: text detection in individual images, framewisely recognizing localized text…

In spite of great success in many image recognition tasks achieved by recent deep models, directly applying them to recognize low-resolution images may suffer from low accuracy due to the missing of informative details during resolution…

Temporal consistency is the key challenge of video depth estimation. Previous works are based on additional optical flow or camera poses, which is time-consuming. By contrast, we derive consistency with less information. Since videos…

Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame…

Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications. However, current solutions are particularly computationally demanding, especially due to the…

We address the weakly supervised video highlight detection problem for learning to detect segments that are more attractive in training videos given their video event label but without expensive supervision of manually annotating highlight…

Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time. The student models are typically compact transformers with fewer parameters, while expensive…

As the development of neural networks, more and more deep neural networks are adopted in various tasks, such as image classification. However, as the huge computational overhead, these networks could not be applied on mobile devices or…

Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision…

We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide…

High accuracy video label prediction (classification) models are attributed to large scale data. These data could be frame feature sequences extracted by a pre-trained convolutional-neural-network, which promote the efficiency for creating…

Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene from different camera views to be available for one-time…

This study tackles the challenge of efficiently classifying streaming data in envi-ronments with limited memory and computational resources. It delves into the application of data distillation as an innovative approach to improve the…

Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing…

This paper studies deep network architectures to address the problem of video classification. A multi-stream framework is proposed to fully utilize the rich multimodal information in videos. Specifically, we first train three Convolutional…

Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm. Based on this paradigm, previous methods…

In video denoising, the adjacent frames often provide very useful information, but accurate alignment is needed before such information can be harnassed. In this work, we present a multi-alignment network, which generates multiple flow…

Decomposing a video into a layer-based representation is crucial for easy video editing for the creative industries, as it enables independent editing of specific layers. Existing video-layer decomposition models rely on implicit neural…