565 citations · 943 across the 50 of their papers we have counts for
10 papers · 1 filter
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
Ilker Kesen, Andrea Pedrotti, Mustafa Dogan +8
With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their v…
Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers
Osman Batur İnce, Tanin Zeraati, Semih Yagcioglu +3
Neural networks have revolutionized language modeling and excelled in various downstream tasks. However, the extent to which these models achieve compositional generalization compa…
Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
Orhan Torun, Seniha Esen Yuksel, Erkut Erdem +2
Compared to natural images, hyperspectral images (HSIs) consist of a large number of bands, with each band capturing different spectral information from a certain wavelength, even…
Spherical Vision Transformer for 360-degree Video Saliency Prediction
Mert Cokelek, Nevrez Imamoglu, Cagri Ozcinar +2
The growing interest in omnidirectional videos (ODVs) that capture the full field-of-view (FOV) has gained 360-degree saliency prediction importance in computer vision. However, pr…
CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing
Ahmet Canberk Baykal, Abdul Basit Anees, Duygu Ceylan +3
Researchers have recently begun exploring the use of StyleGAN-based models for real image editing. One particularly interesting application is using natural language descriptions t…
HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Burak Ercan, Onur Eker, Canberk Saglam +2
Event-based cameras are becoming increasingly popular for their ability to capture high-speed motion with low latency and high dynamic range. However, generating videos from events…
EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction
Burak Ercan, Onur Eker, Aykut Erdem +1
Event cameras are a new type of vision sensor that incorporates asynchronous and independent pixels, offering advantages over traditional frame-based cameras such as high dynamic r…
VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Moayed Haji Ali, Andrew Bond, Tolga Birdal +4
We propose , a spatiotemporally continuous disentangled eo representation based upon GAN and Neural-s. Effective t…
Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
Ahmet Burak Yildirim, Vedat Baday, Erkut Erdem +2
Image inpainting task refers to erasing unwanted pixels from images and filling them in a semantically consistent and realistic way. Traditionally, the pixels that are wished to be…
ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers
Nafiseh Jabbari Tofighi, Mohamed Hedi Elfkir, Nevrez Imamoglu +3
Omnidirectional images, aka 360 images, can deliver immersive and interactive visual experiences. As their popularity has increased dramatically in recent years, evaluating the qua…