Abstract-- Variable length codes (VLCs) exhibit desynchronization problems when transmitted over noisy channels. Trellis decoding techniques based on Maximum A Posteriori (MAP) est...
Simon Malinowski, Herve Jegou, Christine Guillemot
We propose a new approach to estimate gait kinematics from image sequences taken by a monocular uncalibrated camera. This approach involves two generative models for gait represen...
The aim of this work is to investigate how to exploit the temporal information in a video sequence for the task of face recognition. Following the approach in [11], we propose a p...
Capturing the context of a user's query from the previous queries and clicks in the same session may help understand the user's information need. A context-aware approac...
In this paper, we propose a probabilistic method to model the dynamic traffic flow across nonoverlapping camera views. By assuming the transition time of object movement follows a...