Transfer learning enables to re-use knowledge learned on a source task t...
This paper makes a first step towards compatible and hence reusable netw...
In interactive object segmentation a user collaborates with a computer v...
We propose an approach for annotating object classes using free-form tex...
Deep neural networks deliver state-of-the-art visual recognition, but th...
Object class labelling is the task of annotating images with labels on t...
Highlight detection models are typically trained to identify cues that m...
In this paper we present our system for human-in-the-loop video object
s...
Shot boundary detection (SBD) is an important component of many video
an...
Although the problem of automatic video summarization has recently recei...
We approach structured output prediction by optimizing a deep value netw...
Progress in Multiple Object Tracking (MOT) has been historically limited...
We propose a new deep network for audio event recognition, called AENet....