Zobrazeno 1 - 10
of 80
pro vyhledávání: '"Sarvadevabhatla, Ravi Kiran"'
We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion ret
Externí odkaz:
http://arxiv.org/abs/2409.12140
Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation. Existing video recognition approaches work well for common behaviors (e.g. "drive straight", "brake", "turn left/right"). However, the perfor
Externí odkaz:
http://arxiv.org/abs/2405.05354
Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle's driving behavior for safe and efficient navigation. This is particularly critical in developing countries w
Externí odkaz:
http://arxiv.org/abs/2404.08561
Autor:
Khoba, Prafful Kumar, Parikh, Chirag, Saluja, Rohit, Sarvadevabhatla, Ravi Kiran, Jawahar, C. V.
The previous fine-grained datasets mainly focus on classification and are often captured in a controlled setup, with the camera focusing on the objects. We introduce the first Fine-Grained Vehicle Detection (FGVD) dataset in the wild, captured from a
Externí odkaz:
http://arxiv.org/abs/2212.14569
We introduce Action-GPT, a plug-and-play framework for incorporating Large Language Models (LLMs) into text-based action generation models. Action phrases in current motion capture datasets contain minimal and to-the-point information. By carefully c
Externí odkaz:
http://arxiv.org/abs/2211.15603
Autor:
Bansal, Nikhil, Gupta, Kartik, Kannan, Kiruthika, Pentapati, Sivani, Sarvadevabhatla, Ravi Kiran
Pictionary, the popular sketch-based guessing game, provides an opportunity to analyze shared goal cooperative game play in restricted communication settings. However, some players occasionally draw atypical sketch content. While such content is occa
Externí odkaz:
http://arxiv.org/abs/2211.05429
Autor:
Srivastava, Kushagra, Patel, Dhruv, Jha, Aditya Kumar, Jha, Mohhit Kumar, Singh, Jaskirat, Sarvadevabhatla, Ravi Kiran, Ramancharla, Pradeep Kumar, Kandath, Harikumar, Krishna, K. Madhava
Unmanned Aerial Vehicle (UAV) based remote sensing system incorporated with computer vision has demonstrated potential for assisting building construction and in disaster management like damage assessment during earthquakes. The vulnerability of a bu
Externí odkaz:
http://arxiv.org/abs/2209.13418
Pose-based action recognition is predominantly tackled by approaches which treat the input skeleton in a monolithic fashion, i.e. joints in the pose tree are processed as a whole. However, such approaches ignore the fact that action categories are of
Externí odkaz:
http://arxiv.org/abs/2208.05775
Autor:
Goyal, Aman, Agarwal, Dev, Subramanian, Anbumani, Jawahar, C. V., Sarvadevabhatla, Ravi Kiran, Saluja, Rohit
In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles. Identifying and penalizing such riders is vital in curb
Externí odkaz:
http://arxiv.org/abs/2204.08364
Autor:
Shivapuja, Sravya Vardhani, Gopinath, Ashwin, Gupta, Ayush, Ramakrishnan, Ganesh, Sarvadevabhatla, Ravi Kiran
The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting approaches. Specifically, the approaches exhibit unacceptably large standar
Externí odkaz:
http://arxiv.org/abs/2204.04653