Learn More
Recently dense trajectories were shown to be an efficient video representation for action recognition and achieved state-of-the-art results on a variety of datasets. This paper improves their performance by taking into account camera motion to correct them. To estimate camera motion, we match feature points between frames using SURF descriptors and dense(More)
Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However, the quality as well as quantity of these trajectories is often not sufficient. Inspired by the recent success of dense sampling in image classification, we propose an approach to(More)
This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A state-of-the-art optical flow algorithm enables a robust and efficient(More)
Local space-time features have recently become a popular video representation for action recognition. Several methods for feature localization and description have been proposed in the literature and promising recognition results were demonstrated for a number of action classes. The comparison of existing methods, however, is often limited given the(More)
CONTEXT Placebo and nocebo effects, the therapeutic and adverse effects, respectively, of inert substances or sham procedures, represent serious confounds in the evaluation of therapeutic interventions. They are also an example of cognitive processes, particularly expectations, capable of influencing physiology. OBJECTIVE To examine the contribution of 2(More)
This paper introduces a state-of-the-art video representation and applies it to efficient action recognition and detection. We first propose to improve the popular dense trajectory features by explicit camera motion estimation. More specifically, we extract feature point matches between frames using SURF descriptors and dense optical flow. The matches are(More)
This notebook paper describes the submission of the LEAR team from INRIA to the THUMOS workshop in conjunction with ICCV 2013. Our system is based on the recent improvement of dense trajectory feature [14]. After extracting the local features, we apply Fisher vector to integrate them into a compact representation for each video. We also use spatio-temporal(More)
Expectations, positive or negative, are modulating factors influencing behavior. They are also thought to underlie placebo effects, impacting perceptions and biological processes. Using healthy human subjects, we examined the role of the nucleus accumbens (NAC), a region centrally involved in the encoding of reward expectation, in the formation of placebo(More)
In this paper, we present a simplified scheduling scheme for packet transmission over a fading channel which is modeled as a finite state block channel. We first derive the optimal minimum power transmission policy with constraints on both average delay and packet loss. This problem is seen to be the dual problem of the work by Rajan et. al. [1] where the(More)
The endogenous opioid system, which alleviates physical pain, is also known to regulate social distress and reward in animal models. To test this hypothesis in humans (n=18), we used an μ-opioid receptor (MOR) radiotracer to measure changes in MOR availability in vivo with positron emission tomography during social rejection (not being liked by others) and(More)