53 citations · 173 across the 26 of their papers we have counts for
31 papers
Pano3D: Unified 3D Reconstruction and Panoptic Segmentation
Victor Barberteguy, Ahmet Iscen, Mathilde Caron +3
Recent advances in 3D feedforward reconstruction neural networks have achieved remarkable success in dense reconstruction from images without any camera parameters. Yet, equipping…
CAViAR: Critic-Augmented Video Agentic Reasoning
Sachit Menon, Ahmet Iscen, Arsha Nagrani +3
Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
Anurag Arnab, Ahmet Iscen, Mathilde Caron +2
Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 100…
Continual Learning in Vision-Language Models via Aligned Model Merging
Ghada Sokar, Gintare Karolina Dziugaite, Anurag Arnab +3
Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to re…
MINERVA: Evaluating Complex Video Reasoning
Arsha Nagrani, Sachit Menon, Ahmet Iscen +9
Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps.…
Memory-Modular Classification: Learning to Generalize with Memory Replacement
Dahyun Kang, Ahmet Iscen, Eunchan Jo +3
We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes b…
Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach
Mathilde Caron, Alireza Fathi, Cordelia Schmid +1
Web-scale visual entity recognition, the task of associating images with their corresponding entities within vast knowledge bases like Wikipedia, presents significant challenges du…
AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval
Pavel Suma, Giorgos Kordopatis-Zilos, Ahmet Iscen +1
This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image.…
A Generative Approach for Wikipedia-Scale Visual Entity Recognition
Mathilde Caron, Ahmet Iscen, Alireza Fathi +1
In this paper, we address web-scale visual entity recognition, specifically the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. One way…
SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code
Ziniu Hu, Ahmet Iscen, Aashi Jain +5
This paper introduces SceneCraft, a Large Language Model (LLM) Agent converting text descriptions into Blender-executable Python scripts which render complex scenes with up to a hu…
AVIS: Autonomous Visual Information Seeking with Large Language Model Agent
Ziniu Hu, Ahmet Iscen, Chen Sun +5
In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize t…
Retrieval-Enhanced Contrastive Vision-Text Models
Ahmet Iscen, Mathilde Caron, Alireza Fathi +1
Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle o…
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
Ahmet Iscen, Alireza Fathi, Cordelia Schmid
Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabiliti…
REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory
Ziniu Hu, Ahmet Iscen, Chen Sun +6
In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it…
A Memory Transformer Network for Incremental Learning
Ahmet Iscen, Thomas Bird, Mathilde Caron +2
We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulati…
Learning with Neighbor Consistency for Noisy Labels
Ahmet Iscen, Jack Valmadre, Anurag Arnab +1
Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner ofte…
Class-Balanced Distillation for Long-Tailed Visual Recognition
Ahmet Iscen, André Araujo, Boqing Gong +1
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. An effective and simple approach to lo…
Memory-Efficient Incremental Learning Through Feature Adaptation
Ahmet Iscen, Jeffrey Zhang, Svetlana Lazebnik +1
We introduce an approach for incremental learning that preserves feature descriptors of training images from previously learned classes, instead of the images themselves, unlike mo…
Graph convolutional networks for learning with few clean and many noisy labels
Ahmet Iscen, Giorgos Tolias, Yannis Avrithis +2
In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a g…
Label Propagation for Deep Semi-supervised Learning
Ahmet Iscen, Giorgos Tolias, Yannis Avrithis +1
Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Clas…
Local Orthogonal-Group Testing
Ahmet Iscen, Ondrej Chum
This work addresses approximate nearest neighbor search applied in the domain of large-scale image retrieval. Within the group testing framework we propose an efficient off-line co…
Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking
Ahmet Iscen, Yannis Avrithis, Giorgos Tolias +2
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful…
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Filip Radenović, Ahmet Iscen, Giorgos Tolias +2
In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset…