Imran N. Junejo

Ashish Jha, Dimitrii Ermilov, Konstantin Sobolev et al.

Pedestrian Attribute Recognition (PAR) focuses on identifying various attributes in pedestrian images, with key applications in person retrieval, suspect re-identification, and soft biometrics. However, Deep Neural Networks (DNNs) for PAR often suffer from over-parameterization and high computational complexity, making them unsuitable for resource-constrained devices. Traditional tensor-based compression methods typically factorize layers without adequately preserving the gradient direction during compression, leading to inefficient compression and a significant accuracy loss. In this work, we propose a novel approach for determining the optimal ranks of low-rank layers, ensuring that the gradient direction of the compressed model closely aligns with that of the original model. This means that the compressed model effectively preserves the update direction of the full model, enabling more efficient compression for PAR tasks. The proposed procedure optimizes the compression ranks for each layer within the ALM model, followed by compression using CPD-EPC or truncated SVD. This results in a reduction in model complexity while maintaining high performance.

Mohammad Lataifeh, Xavier A Carrascoa, Ashraf M Elnagara et al.

Recent advances in Generative Adversarial Networks GANs applications continue to attract the attention of researchers in different fields. In such a framework, two neural networks compete adversely to generate new visual contents indistinguishable from the original dataset. The objective of this research is to create a complementary codesign process between humans and machines to augment character designers abilities in visualizing and creating new characters for multimedia projects such as games and animation. Driven by design cognitive scaffolding, the proposed approach aims to inform the process of perceiving, knowing, and making. The machine generated concepts are used as a launching platform for character designers to conceptualize new characters. A labelled dataset of 22,000 characters was developed for this work and deployed using different GANs to evaluate the most suited for the context, followed by mixed methods evaluation for the machine output and human derivations. The discussed results substantiate the value of the proposed cocreation framework and elucidate how the generated concepts are used as cognitive substances that interact with designers competencies in a versatile manner to influence the creative processes of conceptualizing novel characters.

Lakshya Gupta, Imran N. Junejo

The computer vision and image processing research community has been involved in standardizing video data communications for the past many decades, leading to standards such as AVC, HEVC, VVC, AV1, AV2, etc. However, recent groundbreaking works have focused on employing deep learning-based techniques to replace the traditional video codec pipeline to a greater affect. Neural video codecs (NVC) create an end-to-end ML-based solution that does not rely on any handcrafted features (motion or edge-based) and have the ability to learn content-aware compression strategies, offering better adaptability and higher compression efficiency than traditional methods. This holds a great potential not only for hardware design, but also for various video streaming platforms and applications, especially video conferencing applications such as MS-Teams or Zoom that have found extensive usage in classrooms and workplaces. However, their high computational demands currently limit their use in real-time applications like video conferencing. To address this, we propose a region-of-interest (ROI) based neural video compression model that leverages 2D Gaussian Splatting. Unlike traditional codecs, 2D Gaussian Splatting is capable of real-time decoding and can be optimized using fewer data points, requiring only thousands of Gaussians for decent quality outputs as opposed to millions in 3D scenes. In this work, we designed a video pipeline that speeds up the encoding time of the previous Gaussian splatting-based image codec by 88% by using a content-aware initialization strategy paired with a novel Gaussian inter-frame redundancy-reduction mechanism, enabling Gaussian splatting to be used for a video-codec solution, the first of its kind solution in this neural video codec space.

Vignesh Edithal, Le Zhang, Ilia Blank et al.

In this work, we enable gamers to share their gaming experience on social media by automatically generating eye-catching highlight reels from their gameplay session Our automation will save time for gamers while increasing audience engagement. We approach the highlight generation problem by first identifying intervals in the video where interesting events occur and then concatenate them. We developed an in-house gameplay event detection dataset containing interesting events annotated by humans using VIA video annotator. Traditional techniques for highlight detection such as game engine integration requires expensive collaboration with game developers. OCR techniques which detect patches of specific images or texts require expensive per game engineering and may not generalize across game UI and different language. We finetuned a multimodal general purpose video understanding model such as X-CLIP using our dataset which generalizes across multiple games in a genre without per game engineering. Prompt engineering was performed to improve the classification performance of this multimodal model. Our evaluation showed that such a finetuned model can detect interesting events in first person shooting games from unseen gameplay footage with more than 90% accuracy. Moreover, our model performed significantly better on low resource games (small dataset) when trained along with high resource games, showing signs of transfer learning. To make the model production ready, we used ONNX libraries to enable cross platform inference. These libraries also provide post training quantization tools to reduce model size and inference time for deployment. ONNX runtime libraries with DirectML backend were used to perform efficient inference on Windows OS. We show that natural language supervision in the X-CLIP model leads to data efficient and highly performant video recognition models.

Akash Haridas, Imran N. Junejo

Applications of generating photo-realistic human avatars are many, however, high-fidelity avatar generation traditionally required expensive professional camera rigs and artistic labor, but recent research has enabled constructing them automatically from smartphones with RGB and IR sensors. However, these new methods still rely on the presence of high-resolution cameras on modern smartphones and often require offloading the processing to powerful servers with GPUs. Modern applications such as video conferencing call for the ability to generate these avatars from consumer-grade laptop webcams using limited compute available on-device. In this work, we develop a novel method based on 3D morphable models, landmark detection, photo-realistic texture GANs, and differentiable rendering to tackle the problem of low webcam image quality and edge computation. We build an automatic system to generate high-fidelity animatable avatars under these limitations, leveraging the neural compute capabilities of mobile chips.