Alert button
Picture for Erkut Erdem

Erkut Erdem

Alert button

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

Nov 13, 2023
Ilker Kesen, Andrea Pedrotti, Mustafa Dogan, Michele Cafagna, Emre Can Acikgoz, Letitia Parcalabescu, Iacer Calixto, Anette Frank, Albert Gatt, Aykut Erdem, Erkut Erdem

Viaarxiv icon

Harnessing Dataset Cartography for Improved Compositional Generalization in Transformers

Oct 18, 2023
Osman Batur İnce, Tanin Zeraati, Semih Yagcioglu, Yadollah Yaghoobzadeh, Erkut Erdem, Aykut Erdem

Viaarxiv icon

Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks

Sep 15, 2023
Orhan Torun, Seniha Esen Yuksel, Erkut Erdem, Nevrez Imamoglu, Aykut Erdem

Figure 1 for Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
Figure 2 for Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
Figure 3 for Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
Figure 4 for Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
Viaarxiv icon

Spherical Vision Transformer for 360-degree Video Saliency Prediction

Aug 24, 2023
Mert Cokelek, Nevrez Imamoglu, Cagri Ozcinar, Erkut Erdem, Aykut Erdem

Figure 1 for Spherical Vision Transformer for 360-degree Video Saliency Prediction
Figure 2 for Spherical Vision Transformer for 360-degree Video Saliency Prediction
Figure 3 for Spherical Vision Transformer for 360-degree Video Saliency Prediction
Figure 4 for Spherical Vision Transformer for 360-degree Video Saliency Prediction
Viaarxiv icon

CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing

Jul 18, 2023
Ahmet Canberk Baykal, Abdul Basit Anees, Duygu Ceylan, Erkut Erdem, Aykut Erdem, Deniz Yuret

Figure 1 for CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing
Figure 2 for CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing
Figure 3 for CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing
Figure 4 for CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing
Viaarxiv icon

HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks

May 10, 2023
Burak Ercan, Onur Eker, Canberk Saglam, Aykut Erdem, Erkut Erdem

Figure 1 for HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Figure 2 for HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Figure 3 for HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Figure 4 for HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Viaarxiv icon

EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction

Apr 30, 2023
Burak Ercan, Onur Eker, Aykut Erdem, Erkut Erdem

Figure 1 for EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction
Viaarxiv icon

VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs

Apr 12, 2023
Moayed Haji Ali, Andrew Bond, Tolga Birdal, Duygu Ceylan, Levent Karacan, Erkut Erdem, Aykut Erdem

Figure 1 for VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Figure 2 for VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Figure 3 for VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Figure 4 for VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
Viaarxiv icon

Inst-Inpaint: Instructing to Remove Objects with Diffusion Models

Apr 06, 2023
Ahmet Burak Yildirim, Vedat Baday, Erkut Erdem, Aykut Erdem, Aysegul Dundar

Figure 1 for Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
Figure 2 for Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
Figure 3 for Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
Figure 4 for Inst-Inpaint: Instructing to Remove Objects with Diffusion Models
Viaarxiv icon

ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers

Mar 13, 2023
Nafiseh Jabbari Tofighi, Mohamed Hedi Elfkir, Nevrez Imamoglu, Cagri Ozcinar, Erkut Erdem, Aykut Erdem

Figure 1 for ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers
Figure 2 for ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers
Figure 3 for ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers
Figure 4 for ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision Transformers
Viaarxiv icon