With the development of image vision technology, video data emerges in large numbers. Even though varieties of methods have achieved excellent performance, how to quickly and accurately retrieve the v...
With emerging demand for large-scale video analysis, MPEG initiated the compact descriptor for video analysis (CDVA) standardization in 2014. Beyond handcrafted descriptors adopted by the current MPEG...
When detecting semantic concepts in video, much of the existing research in content-based classification uses keyframe information only. Particularly the combination between local features such as SIF...
We propose a violence detector based on the dynamics of new multi-scale local binary pattern histogram features (MSLB P), that generate high-dimensional space (20 480 dimensions), trai ned on linear S...
We propose a few-shot adaptation framework, which bridges zero-shot learning and supervised many-shot learning, for semantic indexing of image and video data. Few-shot adaptation provides robust param...
We deal with the issue of combining dozens of classifiers into a better one. Our first contribution is the introduction of the notion of communities of classifiers. We build a complete graph with one ...
We deal with the issue of combining dozens of classifiers into a better one, for concept detection in videos. We compare three fusion approaches that share a common structure: they all start with a cl...
We consider the problem of using image queries to retrieve videos from a database. Our focus is on large-scale applications, where it is infeasible to index each database video frame independently. Ou...
We address the challenge of using image queries to retrieve video clips from a large database. Using binarized Fisher Vectors as global signatures, we present three novel contributions. First, an asym...
Visual concept detection is one of the most active research areas in multimedia analysis. The goal of visual concept detection is to assign to each elementary temporal segment of a video, a confidence...
Video search has become a very important tool, with the ever-growing size of multimedia collections. This work introduces our Video Semantic Indexing system. Our experiments show that Residual Vectors...
This paper tackles the issue of retrieving different instances of an object of interest within a given video document or in a video database. The principle consists of considering a semi-global image ...
This paper tackles the issue of retrieving different instances of an object of interest within a given video document or in a video database. The principle consists in considering a semi-global image ...
This paper reports the experiments carried out for the semantic indexing (SIN) and the instance search (INS) tasks at TRECVID 2012. For the SIN task, we evaluated two recently proposed features with a...
This paper proposes to investigate the potential benefit of the use of low-level human vision behaviors in the context of high-level semantic concept detection. A large part of the current approaches ...
This paper presents an automatic video annotation method which utilizes the user's reading behaviour. Using a wearable eye tracker, we identify the video frames where the user reads a text document an...
This paper presents a set of improvements for SVM-based large scale multimedia indexing. The proposed method is particularly suited for the detection of many target concepts at once and for highly imb...
This paper presents a method for indexing activities of daily living in videos acquired from wearable cameras. It addresses the problematic of analyzing the complex multimedia data acquired from weara...
This paper investigates how the detection of diverse high-level semantic concepts (objects, actions, scene types, persons etc.) in videos can be improved by applying a model of the human retina. A lar...
This paper describes our participation to the TRECVID 2011 challenge [1]. This year, we focused on a stacking fusion with Domain Adaptation algorithm. In machine learning, Domain Adaptation deals with...