1,721,260 research outputs found
Cylindrical Model Based Head Pose Estimation for Drivers
No full textThe application of action recognition algorithms onto driving
safety systems is still an open area of research. In terms of driving
safety, identification of head movements present more significant
information in comparison to other actions of the driver.
Therefore, in this study, we developed a cylindrical model based
head pose estimator to track drivers’ head movements. The experiments
indicate that the proposed scheme presents significant
accuracy in estimation of head pose
Temporal Alignment for History Representation in Reinforcement Learning
No full textEnvironments in Reinforcement Learning are usually only partially observable. To address this problem, a possible solution is to provide the agent with information about the past. However, providing complete observations of numerous steps can be excessive. Inspired by human memory, we propose to represent history with only important changes in the environment and, in our approach, to obtain automatically this representation using self-supervision. Our method (TempAl) aligns temporally-close frames, revealing a general, slowly varying state of the environment. This procedure is based on contrastive loss, which pulls embeddings of nearby observations to each other while pushing away other samples from the batch. It can be interpreted as a metric that captures the temporal relations of observations. We propose to combine both common instantaneous and our history representation and we evaluate TempAl on all available Atari games from the Arcade Learning Environment. TempAl surpasses the instantaneous-only baseline in 35 environments out of 49. The source code of the method and of all the experiments is available at https://github.com/htdt/tempal
StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model
No full textDespite the progress made in the style transfer task, most previous work focus on transferring only relatively simple features like color or texture, while missing more abstract concepts such as overall art expression or painter-specific traits. However, these abstract semantics can be captured by models like DALL-E or CLIP, which have been trained using huge datasets of images and textual documents. In this paper, we propose StylerDALLE, a style transfer method that exploits both of these models and uses natural language to describe abstract art styles. Specifically, we formulate the language-guided style transfer task as a non-autoregressive token sequence translation, i.e., from input content image to output stylized image, in the discrete latent space of a large-scale pretrained vector-quantized tokenizer, e.g., the discrete variational auto-encoder (dVAE) of DALL-E. To incorporate style information, we propose a Reinforcement Learning strategy with CLIP-based language supervision that ensures stylization and content preservation simultaneously. Experimental results demonstrate the superiority of our method, which can effectively transfer art styles using language instructions at different granularities. Code is available at https://github.com/zipengxuc/StylerDALLE
Editorial for the special issue on the DAFNE project (DigitalAnastylosis of Frescoes challeNgE)
No full textEvaluating Multi-task Learning for Multi-view Head-pose Classification in Interactive Environments
No full text
No Matter Where You Are: Flexible Graph-guided Multi-task Learning for Multi-view Head Pose Classification Under Target Motion
No full text
SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective
Full text link- …
