相关论文: DataCube: A Video Retrieval Platform via Natural L…
In this paper, we study the problems of video processing in video search engine. Video has now become a very important kind of data in Internet; while searching for video is still a challenging task due to the inner properties of video:…
Large language models (LLMs) often need to incorporate external knowledge to solve theme-specific problems. Retrieval-augmented generation (RAG) has shown its high promise, empowering LLMs to generate more qualified responses with retrieved…
Despite the success of deep learning in video understanding tasks, processing every frame in a video is computationally expensive and often unnecessary in real-time applications. Frame selection aims to extract the most informative and…
The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit…
Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and candidates. However, current methods either condense queries and candidates into a single vector, potentially limiting the…
Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve…
Networks are widely used to model objects with interactions and have enabled various downstream applications. However, in the real world, network mining is often done on particular query sets of objects, which does not require the…
Recent large vision-language models (LVLMs) for video understanding are primarily fine-tuned with various videos scraped from online platforms. Existing datasets, such as ActivityNet, require considerable human labor for structuring and…
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…
Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of…
This paper explores the task of interactive image retrieval using natural language queries, where a user progressively provides input queries to refine a set of retrieval results. Moreover, our work explores this problem in the context of…
Data visualizations and narratives are often integrated to convey data stories effectively. Among various data storytelling formats, data videos have been garnering increasing attention. These videos provide an intuitive interpretation of…
Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…
Data cubes are used for analyzing large data sets usually contained in data warehouses. The most popular data cube tools use graphical user interfaces (GUI) to do the data analysis. Traditionally this was fine since data analysts were not…
Video classification and analysis is always a popular and challenging field in computer vision. It is more than just simple image classification due to the correlation with respect to the semantic contents of subsequent frames brings…
Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on. The main intent was to enable human viewing of the encoded content. However, with the advances in deep…
We share the implementation details and testing results for video retrieval system based exclusively on features extracted by convolutional neural networks. We show that deep learned features might serve as universal signature for semantic…
As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reconstruction and compression models. However, existing…
Scene-level captioning in instructional videos can enhance learning by requiring an understanding of both visual cues and temporal structure. By aligning visual cues with textual guidance, this understanding supports procedural learning and…
In this demo we present a web-based application for selecting an effective pre-trained dense retriever to use on a private collection. Our system, DenseQuest, provides unsupervised selection and ranking capabilities to predict the best…