Sort by: Year Popularity Relevance
Arnau Ramisa, Yongmei Cheng, Joost van de Weijer, Xialei Liu, Vacit Oguz Yazici, Lu Yu - 2019
Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks. Network distillation has been successfully applied to improve image classificatio...
Jian Dou, Zhen Ye, Pu Zhang, Bohua Zhang, Tao Li, Jianwu Fang, Jianru Xue - 2019
In autonomous driving community, numerous benchmarks have been established to assist the tasks of 3D/2D object detection, stereo vision, semantic/instance segmentation. However, the more meaningful dynamic evolution of the surrounding objects of ego-vehicle is rarely exploited, and lacks a large-scale dataset platform. To address this, we introdu...
Wei Liu, Yunhui Liu, Shengfeng He, Linchao Bao, Jianbo Jiao, Jiangliu Wang - 2019
We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing...
KyungHyun Cho, Rodrigo Nogueira - 2019
Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-imple...
Md Ashraful Alam Milton - 2019
The main essence of this paper is to investigate the performance of RetinaNet based object detectors on pedestrian detection. Pedestrian detection is an important research topic as it provides a baseline for general object detection and has a great number of practical applications like autonomous car, robotics and Security camera. Though extensiv...
Daniel Kondratyuk - 2019
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. By leveraging a multilingual BERT self-attention model pretrained on 104 languages, we found that fine-tu...
Juan Carlos Niebles, Ehsan Adeli, Hsu-kuang Chiu - 2019
Predicting the future is an important aspect for decision-making in robotics or autonomous driving systems, which heavily rely upon visual scene understanding. While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation of the preceding frames, methods that predict f...
Adrien Gaidon, Antonio M. López, Eder Santana, Felipe Codevilla - 2019
Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor pol...
Simon Hadfield, Richard Bowden, Jaime Spencer - 2019
How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered hand-crafted techniques such as HOG, SIFT or ORB. However, there is no ``one size fits all'' approach that ...
Sijie Shen, Yongjie Liu - 2019
Illuminant estimation plays a key role in digital camera pipeline system, it aims at reducing color casting effect due to the influence of non-white illuminant. Recent researches handle this task by using Convolution Neural Network (CNN) as a mapping function from input image to a single illumination vector. However, global mapping approaches are...
