Wildlife recognition in nature documentaries with weak supervision from subtitles and external data

نویسندگان
چکیده

منابع مشابه

Wildlife recognition in nature documentaries with weak supervision from subtitles and external data

We propose a weakly supervised framework for domain adaptation in a multi-modal context for multi-label classification. This framework is applied to annotate objects such as animals in a target video with subtitles, in the absence of visual demarcators. We start from classifiers trained on external data (the source, in our setting ImageNet), and iteratively adapt them to the target dataset usin...

متن کامل

Learning to Recognize Animals by Watching Documentaries: Using Subtitles as Weak Supervision

We investigate animal recognition models learned from wildlife video documentaries by using the weak supervision of the textual subtitles. This is a challenging setting, since i) the animals occur in their natural habitat and are often largely occluded and ii) subtitles are to a great degree complementary to the visual content, providing a very weak supervisory signal. This is in contrast to mo...

متن کامل

Detecting Hunts in Wildlife Documentaries

We propose a multi-level video event detection methodology and apply it to animal hunt detection in wildlife documentaries. The proposed multi-level approach has three levels. The rst level extracts color, texture, and motion features, and detects moving object blobs. The mid-level employs a neural network to verify whether the moving object blobs belong to animals. This level also generates sh...

متن کامل

Summarization of films and documentaries based on subtitles and scripts

We assess the performance of generic text summarization algorithms applied to films and documentaries, using the well–known behavior of summarization of news articles as reference. We use three datasets: (i) news articles, (ii) film scripts and subtitles, and (iii) documentary subtitles. Standard ROUGE metrics are used for comparing generated summaries against news abstracts, plot summaries, an...

متن کامل

Generic Object Recognition with Probabilistic Models and Weak Supervision

Real world images of objects belonging to a particular class typically show large variability in shape, appearance, scale, degree of occlusion, etc. Thus, a major challenge for generic object recognition is to develop object models that are flexible enough to accommodate these large intra-class variabilities. Such powerful models, in turn, require large amounts of training data to be effective ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Pattern Recognition Letters

سال: 2016

ISSN: 0167-8655

DOI: 10.1016/j.patrec.2016.01.025