Motion Invariance in Visual Environments
Authors: Alessandro Betti, Marco Gori, Stefano Melacci
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experiments We implemented a solver for the differential equation of (4) that is based on the Euler method with step size τ. After having reduced the equation to the first order, the variables that were updated at each t are q, q, q, and q(3). The code and data we used to run the following experiments can be downloaded at http://sailab.diism.unisi.it/motion-invariance/, together with the full list of model parameters. We randomly selected two real world video sequences from the Hollywood Dataset HOHA2 [Marszałek et al., 2009], that we will refer to as skater and car , and a clip from the movie The Matrix ( c Warner Bros. Pictures). The frame rate of all the videos is 25 fps (we set τ = 1/25), each frame was rescaled to 240 110 and converted to grayscale. Videos have different lengths, ranging from 10 to 40 seconds, and they were repeated in loop until 45, 000 frames were generated, thus covering a significantly longer time span. We randomly initialized q(0), while the derivatives at time t = 0 were set to 0. We used the softmax function to force a probabilistic activation of the features, and computed the optical flow v using an implementation from the Open CV library. Convolutional filters cover squared areas of the input frame, and we set gx to be the uniform distribution. All the results that we report are averaged over 10 different runs of the algorithms. |
| Researcher Affiliation | Academia | Alessandro Betti1,2 , Marco Gori2 and Stefano Melacci2 1University of Florence, Florence, Italy 2 DIISM, University of Siena, Siena, Italy alessandro.betti@unifi.it, {marco, mela}@diism.unisi.it |
| Pseudocode | No | The paper describes mathematical formulations and a solver implementation but does not present any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Supplementary Material can be found at http://sailab.diism.unisi.it/motion-invariance/. The code and data we used to run the following experiments can be downloaded at http://sailab.diism.unisi.it/motion-invariance/, together with the full list of model parameters. |
| Open Datasets | Yes | We randomly selected two real world video sequences from the Hollywood Dataset HOHA2 [Marszałek et al., 2009] |
| Dataset Splits | No | The paper mentions using video sequences and looping them for extended periods but does not specify explicit training, validation, and test dataset splits. |
| Hardware Specification | No | The paper does not specify any particular hardware components like CPU or GPU models used for the experiments. |
| Software Dependencies | No | The paper mentions 'Open CV library' for optical flow computation, but it does not provide a specific version number for this or any other software dependency. |
| Experiment Setup | Yes | We implemented a solver for the differential equation of (4) that is based on the Euler method with step size τ. After having reduced the equation to the first order, the variables that were updated at each t are q, q, q, and q(3). ... τ = 1/25... We randomly initialized q(0), while the derivatives at time t = 0 were set to 0. We used the softmax function to force a probabilistic activation of the features, and computed the optical flow v using an implementation from the Open CV library. Convolutional filters cover squared areas of the input frame, and we set gx to be the uniform distribution. All the results that we report are averaged over 10 different runs of the algorithms. ... C(x, t) = φ(t)[gauss δ(1 φ(t)) x Co(x, t)]... φ(0) = 0, and then φ is progressively increased as time passes, φ(t+1) = φ(t)+η(1 φ(t)) (we set η = 0.0005). ... If q(t ) 2 ϵ1, or q(t ) 2 ϵ2, or q(3)(t ) 2 ϵ3 then we forced φ(t ) to 0 (ϵj = 300 n, for all j), and then we set to 0 all the derivatives. ... We selected the stability, reality configuration of Fig. 1, that fulfils the conditions of Eq. (7). Changing the video clip does not change the considerations we did so far, while increasing the filter size and number of features can lead to smaller MI index values, mostly due to the need of a better balancing the two entropy terms to cope with the larger number of features. ... ( stability, reality , 5 5 filters, 5 features), and introduced the motion-related term in the cognitive action. ... all the layers ℓ= 1, . . . , 3 share the same value λM that weighs the motion-based term. |