Author name cluster

Gerard Melo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

AAAI Conference 2018 Conference Paper

Multimodal Keyless Attention Fusion for Video Classification

Xiang Long
Chuang Gan
Gerard Melo
Xiao Liu
Yandong Li
Fu Li
Shilei Wen

The problem of video classiﬁcation is inherently sequential and multimodal, and deep neural models hence need to capture and aggregate the most pertinent signals for a given input video. We propose Keyless Attention as an elegant and efﬁcient means to more effectively account for the sequential nature of the data. Moreover, comparing a variety of multimodal fusion methods, we ﬁnd that Multimodal Keyless Attention Fusion is the most successful at discerning interactions between modalities. We experiment on four highly heterogeneous datasets, UCF101, ActivityNet, Kinetics, and YouTube-8M to validate our conclusion, and show that our approach achieves highly competitive results. Especially on large-scale data, our method has great advantages in efﬁciency and performance. Most remarkably, our best single model can achieve 77. 0% in terms of the top-1 accuracy and 93. 2% in terms of the top-5 accuracy on the Kinetics validation set, and achieve 82. 2% in terms of GAP@20 on the ofﬁcial YouTube-8M test set.

PDF Details

AAAI Conference 2016 Conference Paper

Concepts Not Alone: Exploring Pairwise Relationships for Zero-Shot Video Activity Recognition

Chuang Gan
Ming Lin
Yi Yang
Gerard Melo
Alexander G. Hauptmann

Vast quantities of videos are now being captured at astonishing rates, but the majority of these are not labelled. To cope with such data, we consider the task of content-based activity recognition in videos without any manually labelled examples, also known as zero-shot video recognition. To achieve this, videos are represented in terms of detected visual concepts, which are then scored as relevant or irrelevant according to their similarity with a given textual query. In this paper, we propose a more robust approach for scoring concepts in order to alleviate many of the brittleness and low precision problems of previous work. Not only do we jointly consider semantic relatedness, visual reliability, and discriminative power. To handle noise and non-linearities in the ranking scores of the selected concepts, we propose a novel pairwise order matrix approach for score aggregation. Extensive experiments on the large-scale TRECVID Multimedia Event Detection data show the superiority of our approach.

PDF Details

AAAI Conference 2015 Conference Paper

DynaDiffuse: A Dynamic Diffusion Model for Continuous Time Constrained Influence Maximization

Miao Xie
Qiusong Yang
Qing Wang
Gao Cong
Gerard Melo

Studying the spread of phenomena in social networks is critical but still not fully solved. Existing influence maximization models assume a static network, disregarding its evolution over time. We introduce the continuous time constrained influence maximization problem for dynamic diffusion networks, based on a novel diffusion model called DYNADIFFUSE. Although the problem is NP-hard, the influence spread functions are monotonic and submodular, enabling fast approximations on top of an innovative stochastic model checking approach. Experiments on real social network data show that our model finds higher quality solutions and our algorithm outperforms state-of-art alternatives.

PDF Details

AAAI Conference 2014 Conference Paper

Acquiring Comparative Commonsense Knowledge from the Web

Niket Tandon
Gerard Melo
Gerhard Weikum

Applications are increasingly expected to make smart decisions based on what humans consider basic commonsense. An often overlooked but essential form of commonsense involves comparisons, e. g. the fact that bears are typically more dangerous than dogs, that tables are heavier than chairs, or that ice is colder than water. In this paper, we first rely on open information extraction methods to obtain large amounts of comparisons from the Web. We then develop a joint optimization model for cleaning and disambiguating this knowledge with respect to WordNet. This model relies on integer linear programming and semantic coherence scores. Experiments show that our model outperforms strong baselines and allows us to obtain a large knowledge base of disambiguated commonsense assertions.

PDF Details