Publications with Fulltext

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/6

Browse

Filters

2020 - 20224

Advanced Search

Filter by

Settings

Quartile: search.filters.quartile.Q1Subject: search.filters.subject.Artificial intelligence

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    PublicationOpen Access
    End to end rate distortion optimized learned hierarchical bi-directional video compression
    (Institute of Electrical and Electronics Engineers (IEEE), 2022) Department of Electrical and Electronics Engineering; Tekalp, Ahmet Murat; Yılmaz, Mustafa Akın; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 26207; N/A
    Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the combinatorial nature of the end-to-end optimization problem. Learned VC allows end-to-end rate-distortion (R-D) optimized training of nonlinear transform, motion and entropy model simultaneously. Most works on learned VC consider end-to-end optimization of a sequential video codec based on R-D loss averaged over pairs of successive frames. It is well-known in conventional VC that hierarchical, bi-directional coding outperforms sequential compression because of its ability to use both past and future reference frames. This paper proposes a learned hierarchical bi-directional video codec (LHBDC) that combines the benefits of hierarchical motion-compensated prediction and end-to-end optimization. Experimental results show that we achieve the best R-D results that are reported for learned VC schemes to date in both PSNR and MS-SSIM. Compared to conventional video codecs, the R-D performance of our end-to-end optimized codec outperforms those of both x265 and SVT-HEVC encoders ("veryslow" preset) in PSNR and MS-SSIM as well as HM 16.23 reference software in MS-SSIM. We present ablation studies showing performance gains due to proposed novel tools such as learned masking, flow-field subsampling, and temporal flow vector prediction. The models and instructions to reproduce our results can be found in https://github.com/makinyilmaz/LHBDC/.
  • Thumbnail Image
    PublicationOpen Access
    3D microprinting of iron platinum nanoparticle-based magnetic mobile microrobots
    (Wiley, 2021) Giltinan, Joshua; Sridhar, Varun; Bozüyük, Uğur; Sheehan, Devin; Department of Mechanical Engineering; Sitti, Metin; Faculty Member; Department of Mechanical Engineering; School of Medicine; College of Engineering; 297104
    Wireless magnetic microrobots are envisioned to revolutionize minimally invasive medicine. While many promising medical magnetic microrobots are proposed, the ones using hard magnetic materials are not mostly biocompatible, and the ones using biocompatible soft magnetic nanoparticles are magnetically very weak and, therefore, difficult to actuate. Thus, biocompatible hard magnetic micro/nanomaterials are essential toward easy-to-actuate and clinically viable 3D medical microrobots. To fill such crucial gap, this study proposes ferromagnetic and biocompatible iron platinum (FePt) nanoparticle-based 3D microprinting of microrobots using the two-photon polymerization technique. A modified one-pot synthesis method is presented for producing FePt nanoparticles in large volumes and 3D printing of helical microswimmers made from biocompatible trimethylolpropane ethoxylate triacrylate (PETA) polymer with embedded FePt nanoparticles. The 30 mu m long helical magnetic microswimmers are able to swim at speeds of over five body lengths per second at 200Hz, making them the fastest helical swimmer in the tens of micrometer length scale at the corresponding low-magnitude actuation fields of 5-10mT. It is also experimentally in vitro verified that the synthesized FePt nanoparticles are biocompatible. Thus, such 3D-printed microrobots are biocompatible and easy to actuate toward creating clinically viable future medical microrobots.
  • Thumbnail Image
    PublicationOpen Access
    Emotion dependent domain adaptation for speech driven affective facial feature synthesis
    (Institute of Electrical and Electronics Engineers (IEEE), 2022) Department of Electrical and Electronics Engineering; Erzin, Engin; Sadiq, Rizwan; Faculty Member; Department of Electrical and Electronics Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); College of Engineering; 34503; N/A
    Although speech driven facial animation has been studied extensively in the literature, works focusing on the affective content of the speech are limited. This is mostly due to the scarcity of affective audio-visual data. In this article, we improve the affective facial animation using domain adaptation by partially reducing the data scarcity. We first define a domain adaptation to map affective and neutral speech representations to a common latent space in which cross-domain bias is smaller. Then the domain adaptation is used to augment affective representations for each emotion category, including angry, disgust, fear, happy, sad, surprise, and neutral, so that we can better train emotion-dependent deep audio-to-visual (A2V) mapping models. Based on the emotion-dependent deep A2V models, the proposed affective facial synthesis system is realized in two stages: first, speech emotion recognition extracts soft emotion category likelihoods for the utterances; then a soft fusion of the emotion-dependent A2V mapping outputs form the affective facial synthesis. Experimental evaluations are performed on the SAVEE audio-visual dataset. The proposed models are assessed with objective and subjective evaluations. The proposed affective A2V system achieves significant MSE loss improvements in comparison to the recent literature. Furthermore, the resulting facial animations of the proposed system are preferred over the baseline animations in the subjective evaluations.
  • Thumbnail Image
    PublicationOpen Access
    Selection for function: from chemically synthesized prototypes to 3D-printed microdevices
    (Wiley, 2020) Bachmann, Felix; Giltinan, Joshua; Codutti, Agnese; Klumpp, Stefan; Faivre, Damien; Department of Mechanical Engineering; Sitti, Metin; Faculty Member; Department of Mechanical Engineering; School of Medicine; College of Engineering; 297104
    Magnetic microswimmers are promising devices for biomedical and environmental applications. Bacterium flagella-inspired magnetic microhelices with perpendicular magnetizations are currently considered standard for propulsion at low Reynolds numbers because of their well-understood dynamics and controllability. Deviations from this system have recently emerged: randomly shaped magnetic micropropellers with nonlinear swimming behaviors show promise in sensing, sorting, and directional control. The current progresses in 3D micro/nanoprinting allow the production of arbitrary 3D microstructures, increasing the accessible deterministic design space for complex micropropeller morphologies. Taking advantage of this, a shape is systematically reproduced that was formerly identified while screening randomly shaped propellers. Its nonlinear behavior, which is called frequency-induced reversal of swimming direction (FIRSD), allows a propeller to swim in opposing directions by only changing the applied rotating field's frequency. However, the identically shaped swimmers do not only display the abovementioned swimming property but also exhibit a variety of swimming behaviors that are shown to arise from differences in their magnetic moment orientations. This underlines not only the role of shape in microswimmer behavior but also the importance of determining magnetic properties of future micropropellers that act as intelligent devices, as single-shape templates with different magnetic moments can be utilized for different operation modes.