Related papers: Selecting Relevant Web Trained Concepts for Automa…
Event mentions in text correspond to real-world events of varying degrees of granularity. The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes. Since…
Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles. Existing methods focus on capturing the overall visual scene of each frame, ignoring fine-grained…
Accurately retrieving images that are semantically similar remains a fundamental challenge in computer vision, as traditional methods often fail to capture the relational and contextual nuances of a scene. We introduce PRISm (Pruning-based…
Video moment retrieval (MR) and highlight detection (HD) with natural language queries aim to localize relevant moments and key highlights in a video clips. However, existing methods overlook the importance of individual words, treating the…
We present a novel framework for finding complex activities matching user-described queries in cluttered surveillance videos. The wide diversity of queries coupled with unavailability of annotated activity data limits our ability to train…
The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and the overlap between these tasks, recent works have addressed…
This paper presents a novel retrieval pipeline for video collections, which aims to retrieve the most significant parts of an edited video for a given query, and represent them with thumbnails which are at the same time semantically…
Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate to visually discriminative entities. We propose an…
Detecting complex events in a large video collection crawled from video websites is a challenging task. When applying directly good image-based feature representation, e.g., HOG, SIFT, to videos, we have to face the problem of how to pool…
Retrieving images from natural language descriptions is a core task at the intersection of computer vision and natural language processing, with wide-ranging applications in search engines, media archiving, and digital content management.…
Text in natural images contains rich semantics that are often highly relevant to objects or scene. In this paper, we focus on the problem of fully exploiting scene text for visual understanding. The main idea is combining word…
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video…
Our objective is video retrieval based on natural language queries. In addition, we consider the analogous problem of retrieving sentences or generating descriptions given an input video. Recent work has addressed the problem by embedding…
Visual concept composition, which aims to integrate different elements from images and videos into a single, coherent visual output, still falls short in accurately extracting complex concepts from visual inputs and flexibly combining…
Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…
A thorough comprehension of image content demands a complex grasp of the interactions that may occur in the natural world. One of the key issues is to describe the visual relationships between objects. When dealing with real world data,…
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages…
The goal of text-to-video retrieval is to search large databases for relevant videos based on text queries. Existing methods have progressed to handling explicit queries where the visual content of interest is described explicitly; however,…
Video moment retrieval is to identify the target moment according to the given sentence in an untrimmed video. Due to temporal boundary annotations of the video are extremely time-consuming to acquire, modeling in the weakly-supervised…
Most previous studies of document-level event extraction mainly focus on building argument chains in an autoregressive way, which achieves a certain success but is inefficient in both training and inference. In contrast to the previous…