Výsledky vyhledávání - "Aafaq, Nayyer"

Report

Randomize to Generalize: Domain Randomization for Runway FOD Detection

Autor: Farooq, Javaria, Aafaq, Nayyer, Khan, M Khizer Ali, Saleem, Ammar, Siddiqui, M Ibraheem

Tiny Object Detection is challenging due to small size, low resolution, occlusion, background clutter, lighting conditions and small object-to-image ratio. Further, object detection methodologies often make underlying assumption that both training an

Externí odkaz: http://arxiv.org/abs/2309.13264

Zobrazit plný text záznamu

Report

Controlled Caption Generation for Images Through Adversarial Attacks

Autor: Aafaq, Nayyer, Akhtar, Naveed, Liu, Wei, Shah, Mubarak, Mian, Ajmal

Deep learning is found to be vulnerable to adversarial examples. However, its adversarial susceptibility in image caption generation is under-explored. We study adversarial examples for vision and language models, which typically adopt an encoder-dec

Externí odkaz: http://arxiv.org/abs/2107.03050

Zobrazit plný text záznamu

Report

Empirical Autopsy of Deep Video Captioning Frameworks

Autor: Aafaq, Nayyer, Akhtar, Naveed, Liu, Wei, Mian, Ajmal

Contemporary deep learning based video captioning follows encoder-decoder framework. In encoder, visual features are extracted with 2D/3D Convolutional Neural Networks (CNNs) and a transformed version of those features is passed to the decoder. The d

Externí odkaz: http://arxiv.org/abs/1911.09345

Zobrazit plný text záznamu

Report

Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning

Autor: Aafaq, Nayyer, Akhtar, Naveed, Liu, Wei, Gilani, Syed Zulqarnain, Mian, Ajmal

Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods ma

Externí odkaz: http://arxiv.org/abs/1902.10322

Zobrazit plný text záznamu

Report

Video Description: A Survey of Methods, Datasets and Evaluation Metrics

Autor: Aafaq, Nayyer, Mian, Ajmal, Liu, Wei, Gilani, Syed Zulqarnain, Shah, Mubarak

Publikováno v: ACM Computing Surveys (CSUR) 52(6), 115 (2019)

Video description is the automatic generation of natural language sentences that describe the contents of a given video. It has applications in human-robot interaction, helping the visually impaired and video subtitling. The past few years have seen

Externí odkaz: http://arxiv.org/abs/1806.00186

Zobrazit plný text záznamu