Related papers: Activitynet 2019 Task 3: Exploring Contexts for De…
Modeling long-term context in videos is crucial for many fine-grained tasks including temporal action segmentation. An interesting question that is still open is how much long-term temporal context is needed for optimal performance. While…
Automatic video captioning is challenging due to the complex interactions in dynamic real scenes. A comprehensive system would ultimately localize and track the objects, actions and interactions present in a video and generate a description…
Accelerated by the tremendous increase in Internet bandwidth and storage space, video data has been generated, published and spread explosively, becoming an indispensable part of today's big data. In this paper, we focus on reviewing two…
While deep-learning models have been shown to perform well on image-to-text datasets, it is difficult to use them in practice for captioning images. This is because captions traditionally tend to be context-dependent and offer complementary…
Automatically describing video content with text description is challenging but important task, which has been attracting a lot of attention in computer vision community. Previous works mainly strive for the accuracy of the generated…
Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress,…
Video captioning is an essential technology to understand scenes and describe events in natural language. To apply it to real-time monitoring, a system needs not only to describe events accurately but also to produce the captions as soon as…
Recently, dense video captioning has made attractive progress in detecting and captioning all events in a long untrimmed video. Despite promising results were achieved, most existing methods do not sufficiently explore the scene evolution…
We introduce dense relational captioning, a novel image captioning task which aims to generate multiple captions with respect to relational information between objects in a visual scene. Relational captioning provides explicit descriptions…
The task of video-based commonsense captioning aims to generate event-wise captions and meanwhile provide multiple commonsense descriptions (e.g., attribute, effect and intention) about the underlying event in the video. Prior works explore…
3D dense captioning, as an emerging vision-language task, aims to identify and locate each object from a set of point clouds and generate a distinctive natural language sentence for describing each located object. However, the existing…
We present our submission to the Microsoft Video to Language Challenge of generating short captions describing videos in the challenge dataset. Our model is based on the encoder--decoder pipeline, popular in image and video captioning…
While there is overall agreement that future technology for organizing, browsing and searching videos hinges on the development of methods for high-level semantic understanding of video, so far no consensus has been reached on the best way…
This paper introduces our solution for Track 2 in AI City Challenge 2024. The task aims to solve traffic safety description and analysis with the dataset of Woven Traffic Safety (WTS), a real-world Pedestrian-Centric Traffic Video Dataset…
The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted…
This paper proposes a network architecture to perform variable length semantic video generation using captions. We adopt a new perspective towards video generation where we allow the captions to be combined with the long-term and short-term…
Most prior art in visual understanding relies solely on analyzing the "what" (e.g., event recognition) and "where" (e.g., event localization), which in some cases, fails to describe correct contextual relationships between events or leads…
This paper proposes a practical multimodal video summarization task setting and a dataset to train and evaluate the task. The target task involves summarizing a given video into a predefined number of keyframe-caption pairs and displaying…
Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract visual-relevant textual prompts to…
Image Captioning is a task that requires models to acquire a multi-modal understanding of the world and to express this understanding in natural language text. While the state-of-the-art for this task has rapidly improved in terms of n-gram…