Özgür Kara

Bikram Boote, Anh Thai, Wenqi Jia et al.

Point tracking is a fundamental problem in computer vision with numerous applications in AR and robotics. A common failure mode in long-term point tracking occurs when the predicted point leaves the object it belongs to and lands on the background or another object. We identify this as the failure to correctly capture objectness properties in learning to track. To address this limitation of prior work, we propose a novel objectness regularization approach that guides points to be aware of object priors by forcing them to stay inside the the boundaries of object instances. By capturing objectness cues at training time, we avoid the need to compute object masks during testing. In addition, we leverage contextual attention to enhance the feature representation for capturing objectness at the feature level more effectively. As a result, our approach achieves state-of-the-art performance on three point tracking benchmarks, and we further validate the effectiveness of our components via ablation studies. The source code is available at: https://github.com/RehgLab/tracking_objectness

Ozgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe et al.

Recent advancements in diffusion-based models have demonstrated significant success in generating images from text. However, video editing models have not yet reached the same level of visual quality and user control. To address this, we introduce RAVE, a zero-shot video editing method that leverages pre-trained text-to-image diffusion models without additional training. RAVE takes an input video and a text prompt to produce high-quality videos while preserving the original motion and semantic structure. It employs a novel noise shuffling strategy, leveraging spatio-temporal interactions between frames, to produce temporally consistent videos faster than existing methods. It is also efficient in terms of memory requirements, allowing it to handle longer videos. RAVE is capable of a wide range of edits, from local attribute modifications to shape transformations. In order to demonstrate the versatility of RAVE, we create a comprehensive video evaluation dataset ranging from object-focused scenes to complex human activities like dancing and typing, and dynamic scenes featuring swimming fish and boats. Our qualitative and quantitative experiments highlight the effectiveness of RAVE in diverse video editing scenarios compared to existing methods. Our code, dataset and videos can be found in https://rave-video.github.io.

Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin et al.

Current image immunization defense techniques against diffusion-based editing embed imperceptible noise in target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming re-optimization for each image-taking hours for small batches. To address these challenges, we introduce DiffVax, a scalable, lightweight, and optimization-free framework for image immunization, specifically designed to prevent diffusion-based editing. Our approach enables effective generalization to unseen content, reducing computational costs and cutting immunization time from days to milliseconds-achieving a 250,000x speedup. This is achieved through a loss term that ensures the failure of editing attempts and the imperceptibility of the perturbations. Extensive qualitative and quantitative results demonstrate that our model is scalable, optimization-free, adaptable to various diffusion-based editing tools, robust against counter-attacks, and, for the first time, effectively protects video content from editing. Our code is provided in our project webpage.

Metin Ersin Arican, Ozgur Kara, Gustav Bredell et al.

Recent works show that convolutional neural network (CNN) architectures have a spectral bias towards lower frequencies, which has been leveraged for various image restoration tasks in the Deep Image Prior (DIP) framework. The benefit of the inductive bias the network imposes in the DIP framework depends on the architecture. Therefore, researchers have studied how to automate the search to determine the best-performing model. However, common neural architecture search (NAS) techniques are resource and time-intensive. Moreover, best-performing models are determined for a whole dataset of images instead of for each image independently, which would be prohibitively expensive. In this work, we first show that optimal neural architectures in the DIP framework are image-dependent. Leveraging this insight, we then propose an image-specific NAS strategy for the DIP framework that requires substantially less training than typical NAS approaches, effectively enabling image-specific NAS. We justify the proposed strategy's effectiveness by (1) demonstrating its performance on a NAS Dataset for DIP that includes 522 models from a particular search space (2) conducting extensive experiments on image denoising, inpainting, and super-resolution tasks. Our experiments show that image-specific metrics can reduce the search space to a small cohort of models, of which the best model outperforms current NAS approaches for image restoration. Codes and datasets are available at https://github.com/ozgurkara99/ISNAS-DIP.

Ahmet Alp Kindiroglu, Ozgur Kara, Ogulcan Ozdemir et al.

Sign language recognition (SLR) has recently achieved a breakthrough in performance thanks to deep neural networks trained on large annotated sign datasets. Of the many different sign languages, these annotated datasets are only available for a select few. Since acquiring gloss-level labels on sign language videos is difficult, learning by transferring knowledge from existing annotated sources is useful for recognition in under-resourced sign languages. This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets. We use a temporal graph convolution-based sign language recognition approach to evaluate five supervised transfer learning approaches and experiment with closed-set and partial-set cross-dataset transfer learning. Experiments demonstrate that improvement over finetuning based transfer learning is possible with specialized supervised transfer learning methods.

Ozgur Kara, Krishna Kumar Singh, Feng Liu et al.

Current diffusion-based text-to-video methods are limited to producing short video clips of a single shot and lack the capability to generate multi-shot videos with discrete transitions where the same character performs distinct activities across the same or different backgrounds. To address this limitation we propose a framework that includes a dataset collection pipeline and architectural extensions to video diffusion models to enable text-to-multi-shot video generation. Our approach enables generation of multi-shot videos as a single video with full attention across all frames of all shots, ensuring character and background consistency, and allows users to control the number, duration, and content of shots through shot-specific conditioning. This is achieved by incorporating a transition token into the text-to-video model to control at which frames a new shot begins and a local attention masking strategy which controls the transition token's effect and allows shot-specific prompting. To obtain training data we propose a novel data collection pipeline to construct a multi-shot video dataset from existing single-shot video datasets. Extensive experiments demonstrate that fine-tuning a pre-trained text-to-video model for a few thousand iterations is enough for the model to subsequently be able to generate multi-shot videos with shot-specific control, outperforming the baselines. You can find more details in https://shotadapter.github.io/

Ozgur Kara, Yujia Chen, Ming-Hsuan Yang et al.

We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM splits a large corpus of unlabeled videos into dynamic foreground and background layers, then self-composes them to learn how dynamic subjects interact with diverse scenes. This process enables the model to learn the complex compositional dynamics required for realistic video generation. StM introduces a novel transformation-aware training pipeline that utilizes a multi-layer fusion and augmentation to achieve affordance-aware composition, alongside an identity-preservation loss that maintains foreground fidelity during blending. Experiments show StM outperforms SoTA methods in both quantitative benchmarks and in humans/VLLM-based qualitative evaluations. More details are available at our project page: https://split-then-merge.github.io

Ozgur Kara, Nikhil Churamani, Hatice Gunes

As affective robots become integral in human life, these agents must be able to fairly evaluate human affective expressions without discriminating against specific demographic groups. Identifying bias in Machine Learning (ML) systems as a critical problem, different approaches have been proposed to mitigate such biases in the models both at data and algorithmic levels. In this work, we propose Continual Learning (CL) as an effective strategy to enhance fairness in Facial Expression Recognition (FER) systems, guarding against biases arising from imbalances in data distributions. We compare different state-of-the-art bias mitigation approaches with CL-based strategies for fairness on expression recognition and Action Unit (AU) detection tasks using popular benchmarks for each; RAF-DB and BP4D. Our experiments show that CL-based methods, on average, outperform popular bias mitigation techniques, strengthening the need for further investigation into CL for the development of fairer FER algorithms.