Scalable graph-based bug search for firmware images
Because of rampant security breaches in IoT devices, searching vulnerabilities in massive
IoT ecosystems is more crucial than ever. Recent studies have demonstrated that control …
IoT ecosystems is more crucial than ever. Recent studies have demonstrated that control …
Self-paced curriculum learning
Curriculum learning (CL) or self-paced learning (SPL) represents a recently proposed
learning regime inspired by the learning process of humans and animals that gradually …
learning regime inspired by the learning process of humans and animals that gradually …
Self-paced learning with diversity
Self-paced learning (SPL) is a recently proposed learning regime inspired by the learning
process of humans and animals that gradually incorporates easy to more complex samples …
process of humans and animals that gradually incorporates easy to more complex samples …
Easy samples first: Self-paced reranking for zero-example multimedia search
Reranking has been a focal technique in multimedia retrieval due to its efficacy in improving
initial retrieval results. Current reranking methods, however, mainly rely on the heuristic …
initial retrieval results. Current reranking methods, however, mainly rely on the heuristic …
Event-based media processing and analysis: A survey of the literature
Research on event-based processing and analysis of media is receiving an increasing
attention from the scientific community due to its relevance for an abundance of applications …
attention from the scientific community due to its relevance for an abundance of applications …
Objects2action: Classifying and localizing actions without any video example
The goal of this paper is to recognize actions in video without the need for examples.
Different from traditional zero-shot approaches we do not demand the design and …
Different from traditional zero-shot approaches we do not demand the design and …
Exploring semantic inter-class relationships (sir) for zero-shot action recognition
Automatically recognizing a large number of action categories from videos is of significant
importance for video understanding. Most existing works focused on the design of more …
importance for video understanding. Most existing works focused on the design of more …
Video2vec embeddings recognize events when examples are scarce
A Habibian, T Mensink… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
This paper aims for event recognition when video examples are scarce or even completely
absent. The key in such a challenging setting is a semantic video representation. Rather …
absent. The key in such a challenging setting is a semantic video representation. Rather …
New modality: Emoji challenges in prediction, anticipation, and retrieval
S Cappallo, S Svetlichnaya, P Garrigues… - IEEE Transactions …, 2018 - ieeexplore.ieee.org
Over the past decade, emoji have emerged as a new and widespread form of digital
communication, spanning diverse social networks and spoken languages. We propose …
communication, spanning diverse social networks and spoken languages. We propose …
Decomposition-based evolutionary multiobjective optimization to self-paced learning
Self-paced learning (SPL) is a recently proposed paradigm to imitate the learning process of
humans/animals. SPL involves easier samples into training at first and then gradually takes …
humans/animals. SPL involves easier samples into training at first and then gradually takes …