Loris Bazzani

Mengmeng Xu, Erhan Gundogdu, Maksim Lapin et al.

Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations at large-scale. These limitations can be addressed by pre-training on large datasets of temporally trimmed videos supervised by class annotations. Once the video encoder is pre-trained, it is common practice to freeze it during fine-tuning. Therefore, the video encoder does not learn temporal boundaries and unseen classes, causing a domain gap with respect to the downstream tasks. Moreover, using temporally trimmed videos prevents to capture the relations between different action categories and the background context in a video clip which results in limited generalization capacity. To address these limitations, we propose a novel post-pre-training approach without freezing the video encoder which leverages language. We introduce a masked contrastive learning loss to capture visio-linguistic relations between activities, background video clips and language in the form of captions. Our experiments show that the proposed approach improves the state-of-the-art on temporal action localization, few-shot temporal action localization, and video language grounding tasks.

Aavash Chhetri, Bibek Niroula, Pratik Shrestha et al.

Federated learning (FL) enables collaborative model training across decentralized medical institutions while preserving data privacy. However, medical FL benchmarks remain scarce, with existing efforts focusing mainly on unimodal or bimodal modalities and a limited range of medical tasks. This gap underscores the need for standardized evaluation to advance systematic understanding in medical MultiModal FL (MMFL). To this end, we introduce Med-MMFL, the first comprehensive MMFL benchmark for the medical domain, encompassing diverse modalities, tasks, and federation scenarios. Our benchmark evaluates six representative state-of-the-art FL algorithms, covering different aggregation strategies, loss formulations, and regularization techniques. It spans datasets with 2 to 4 modalities, comprising a total of 10 unique medical modalities, including text, pathology images, ECG, X-ray, radiology reports, and multiple MRI sequences. Experiments are conducted across naturally federated, synthetic IID, and synthetic non-IID settings to simulate real-world heterogeneity. We assess segmentation, classification, modality alignment (retrieval), and VQA tasks. To support reproducibility and fair comparison of future multimodal federated learning (MMFL) methods under realistic medical settings, we release the complete benchmark implementation, including data processing and partitioning pipelines, at https://github.com/bhattarailab/Med-MMFL-Benchmark .

Nikesh Subedi, Loris Bazzani, Ziad Al-Halah

In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., "Where did I place the mug?") that requires searching a long egocentric video, captured from the user's perspective, to find the moment that answers it. However, queries can be ambiguous or incomplete, leading to incorrect responses. Current methods ignore this key aspect and address EM-NLQ in a one-shot setup, limiting their applicability in real-world scenarios. In this work, we address this gap and introduce the Episodic Memory with Questions and Feedback task (EM-QnF). Here, the user can provide feedback on the model's initial prediction or add more information (e.g., "Before this. I'm looking for the big blue mug not the white one"), helping the model refine its predictions interactively. To this end, we collect datasets for feedback-based interaction and propose a lightweight training scheme that avoids expensive sequential optimization. We also introduce a plug-and-play Feedback ALignment Module (FALM) that enables existing EM-NLQ models to incorporate user feedback effectively. Our approach significantly improves over the state of the art on three challenging benchmarks and is better than or competitive with commercial large vision-language models while remaining efficient. Evaluation with human-generated feedback shows that it generalizes well to real-world scenarios.

Edoardo Zorzi, Francesco Taioli, Yiming Wang et al.

We propose Question-Asking Navigation (QAsk-Nav), the first reproducible benchmark for Collaborative Instance Object Navigation (CoIN) that enables an explicit, separate assessment of embodied navigation and collaborative question asking. CoIN tasks an embodied agent with reaching a target specified in free-form natural language under partial observability, using only egocentric visual observations and interactive natural-language dialogue with a human, where the dialogue can help to resolve ambiguity among visually similar object instances. Existing CoIN benchmarks are primarily focused on navigation success and offer no support for consistent evaluation of collaborative interaction. To address this limitation, QAsk-Nav provides (i) a lightweight question-asking protocol scored independently of navigation, (ii) an enhanced navigation protocol with realistic, diverse, high-quality target descriptions, and (iii) an open-source dataset, that includes 28,000 quality-checked reasoning and question-asking traces for training and analysis of interactive capabilities of CoIN models. Using the proposed QAsk-Nav benchmark, we develop Light-CoNav, a lightweight unified model for collaborative navigation that is 3x smaller and 70x faster than existing modular methods, while outperforming state-of-the-art CoIN approaches in generalization to unseen objects and environments. Project page at https://benchmarking-interaction.github.io/

Loris Bazzani, Tobias Domhan, Felix Hieber

Image captioning is an interdisciplinary research problem that stands between computer vision and natural language processing. The task is to generate a textual description of the content of an image. The typical model used for image captioning is an encoder-decoder deep network, where the encoder captures the essence of an image while the decoder is responsible for generating a sentence describing the image. Attention mechanisms can be used to automatically focus the decoder on parts of the image which are relevant to predict the next word. In this paper, we explore different decoders and attentional models popular in neural machine translation, namely attentional recurrent neural networks, self-attentional transformers, and fully-convolutional networks, which represent the current state of the art of neural machine translation. The image captioning module is available as part of SOCKEYE at https://github.com/awslabs/sockeye which tutorial can be found at https://awslabs.github.io/sockeye/image_captioning.html .

Xianghui Yang, Yan Zuo, Sameera Ramasinghe et al.

Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in maintaining multiple-view consistency. To address this, we introduce ViewFusion, a novel, training-free algorithm that can be seamlessly integrated into existing pre-trained diffusion models. Our approach adopts an auto-regressive method that implicitly leverages previously generated views as context for the next view generation, ensuring robust multi-view consistency during the novel-view generation process. Through a diffusion process that fuses known-view information via interpolated denoising, our framework successfully extends single-view conditioned models to work in multiple-view conditional settings without any additional fine-tuning. Extensive experimental results demonstrate the effectiveness of ViewFusion in generating consistent and detailed novel views.

Ziyue Liu, Davide Talon, Federico Girella et al.

Sketches offer designers a concise yet expressive medium for early-stage fashion ideation by specifying structure, silhouette, and spatial relationships, while textual descriptions complement sketches to convey material, color, and stylistic details. Effectively combining textual and visual modalities requires adherence to the sketch visual structure when leveraging the guidance of localized attributes from text. We present LOcalized Text and Sketch with multi-level guidance (LOTS), a framework that enhances fashion image generation by combining global sketch guidance with multiple localized sketch-text pairs. LOTS employs a Multi-level Conditioning Stage to independently encode local features within a shared latent space while maintaining global structural coordination. Then, the Diffusion Pair Guidance stage integrates both local and global conditioning via attention-based guidance within the diffusion model's multi-step denoising process. To validate our method, we develop Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Sketchy provides high-quality, clean sketches with a professional look and consistent structure. To assess robustness beyond this setting, we also include an "in the wild" split with non-expert sketches, featuring higher variability and imperfections. Experiments demonstrate that our method strengthens global structural adherence while leveraging richer localized semantic guidance, achieving improvement over state-of-the-art. The dataset, platform, and code are publicly available.

Vittorio Pippi, Matthieu Guillaumin, Silvia Cascianelli et al.

Large Multimodal Models (LMMs) are powerful tools that are capable of reasoning and understanding multimodal information beyond text and language. Despite their entrenched impact, the development of LMMs is hindered by the higher computational requirements compared to their unimodal counterparts. One of the main causes of this is the large amount of tokens needed to encode the visual input, which is especially evident for multi-image multimodal tasks. Recent approaches to reduce visual tokens depend on the visual encoder architecture, require fine-tuning the LLM to maintain the performance, and only consider single-image scenarios. To address these limitations, we propose ToFu, a visual encoder-agnostic, training-free Token Fusion strategy that combines redundant visual tokens of LMMs for high-resolution, multi-image, tasks. The core intuition behind our method is straightforward yet effective: preserve distinctive tokens while combining similar ones. We achieve this by sequentially examining visual tokens and deciding whether to merge them with others or keep them as separate entities. We validate our approach on the well-established LLaVA-Interleave Bench, which covers challenging multi-image tasks. In addition, we push to the extreme our method by testing it on a newly-created benchmark, ComPairs, focused on multi-image comparisons where a larger amount of images and visual tokens are inputted to the LMMs. Our extensive analysis, considering several LMM architectures, demonstrates the benefits of our approach both in terms of efficiency and performance gain.

Maximilian Jaritz, Matthieu Guillaumin, Sabine Sternig et al.

Multimodal retrieval methods have limitations in handling complex, compositional queries that require reasoning about the visual content of both the query and the retrieved entities. On the other hand, Large Multimodal Models (LMMs) can answer with language to more complex visual questions, but without the inherent ability to retrieve relevant entities to support their answers. We aim to address these limitations with UniCoRN, a Unified Commented Retrieval Network that combines the strengths of composed multimodal retrieval methods and generative language approaches, going beyond Retrieval-Augmented Generation (RAG). We introduce an entity adapter module to inject the retrieved multimodal entities back into the LMM, so it can attend to them while generating answers and comments. By keeping the base LMM frozen, UniCoRN preserves its original capabilities while being able to perform both retrieval and text generation tasks under a single integrated framework. To assess these new abilities, we introduce the Commented Retrieval task (CoR) and a corresponding dataset, with the goal of retrieving an image that accurately answers a given question and generate an additional textual response that provides further clarification and details about the visual information. We demonstrate the effectiveness of UniCoRN on several datasets showing improvements of +4.5% recall over the state of the art for composed multimodal retrieval and of +14.9% METEOR / +18.4% BEM over RAG for commenting in CoR.

Ziwei Wang, Sameera Ramasinghe, Chenchen Xu et al.

Structuring latent representations in a hierarchical manner enables models to learn patterns at multiple levels of abstraction. However, most prevalent image understanding models focus on visual similarity, and learning visual hierarchies is relatively unexplored. In this work, for the first time, we introduce a learning paradigm that can encode user-defined multi-level complex visual hierarchies in hyperbolic space without requiring explicit hierarchical labels. As a concrete example, first, we define a part-based image hierarchy using object-level annotations within and across images. Then, we introduce an approach to enforce the hierarchy using contrastive loss with pairwise entailment metrics. Finally, we discuss new evaluation metrics to effectively measure hierarchical image retrieval. Encoding these complex relationships ensures that the learned representations capture semantic and structural information that transcends mere visual similarity. Experiments in part-based image retrieval show significant improvements in hierarchical retrieval tasks, demonstrating the capability of our model in capturing visual hierarchies.

Rumeysa Bodur, Erhan Gundogdu, Binod Bhattarai et al.

Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for text-guided image editing, namely \texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving the fidelity of the source image. We propose to automatically construct a dataset derived from LAION-5B, containing pseudo-target images with their descriptive edit prompts given input image-caption pairs. This dataset gives us the flexibility of introducing a weakly-supervised loss function to generate the pseudo-target image from the latent noise of the source image conditioned on the edit prompt. To encourage localised editing and preserve or modify spatial structures in the image, we propose a loss function that uses segmentation masks to guide the editing during training and optionally at inference. Our model is trained on the constructed dataset with 200K samples and constrained GPU resources. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.

Amaia Salvador, Erhan Gundogdu, Loris Bazzani et al.

Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives, as well as the availability of vast amounts of digital cooking recipes and food images to train machine learning models. In this work, we revisit existing approaches for cross-modal recipe retrieval and propose a simplified end-to-end model based on well established and high performing encoders for text and images. We introduce a hierarchical recipe Transformer which attentively encodes individual recipe components (titles, ingredients and instructions). Further, we propose a self-supervised loss function computed on top of pairs of individual recipe components, which is able to leverage semantic relationships within recipes, and enables training using both image-recipe and recipe-only samples. We conduct a thorough analysis and ablation studies to validate our design choices. As a result, our proposed method achieves state-of-the-art performance in the cross-modal recipe retrieval task on the Recipe1M dataset. We make code and models publicly available.

Hà Quang Minh, Marco San Biagio, Loris Bazzani et al.

This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds. Our formulation provides in particular a rich representation of image features by exploiting their non-linear correlations. Theoretically, we provide a finite-dimensional approximation of the Log-Hilbert-Schmidt (Log-HS) distance between covariance operators that is scalable to large datasets, while maintaining an effective discriminating capability. This allows us to efficiently approximate any continuous shift-invariant kernel defined using the Log-HS distance. At the same time, we prove that the Log-HS inner product between covariance operators is only approximable by its finite-dimensional counterpart in a very limited scenario. Consequently, kernels defined using the Log-HS inner product, such as polynomial kernels, are not scalable in the same way as shift-invariant kernels. Computationally, we apply the approximate Log-HS distance formulation to covariance operators of both handcrafted and convolutional features, exploiting both the expressiveness of these features and the power of the covariance representation. Empirically, we tested our framework on the task of image classification on twelve challenging datasets. In almost all cases, the results obtained outperform other state of the art methods, demonstrating the competitiveness and potential of our framework.

Loris Bazzani, Hugo Larochelle, Lorenzo Torresani

In many computer vision tasks, the relevant information to solve the problem at hand is mixed to irrelevant, distracting information. This has motivated researchers to design attentional models that can dynamically focus on parts of images or videos that are salient, e.g., by down-weighting irrelevant pixels. In this work, we propose a spatiotemporal attentional model that learns where to look in a video directly from human fixation data. We model visual attention with a mixture of Gaussians at each frame. This distribution is used to express the probability of saliency for each pixel. Time consistency in videos is modeled hierarchically by: 1) deep 3D convolutional features to represent spatial and short-term time relations and 2) a long short-term memory network on top that aggregates the clip-level representation of sequential clips and therefore expands the temporal domain from few frames to seconds. The parameters of the proposed model are optimized via maximum likelihood estimation using human fixations as training data, without knowledge of the action in each video. Our experiments on Hollywood2 show state-of-the-art performance on saliency prediction for video. We also show that our attentional model trained on Hollywood2 generalizes well to UCF101 and it can be leveraged to improve action classification accuracy on both datasets.

Loris Bazzani, Alessandro Bergamo, Dragomir Anguelov et al.

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using any ground-truth bounding boxes for training. The key idea is to analyze the change in the recognition scores when artificially masking out different regions of the image. The masking out of a region that includes the object typically causes a significant drop in recognition score. This idea is embedded into an agglomerative clustering technique that generates self-taught localization hypotheses. Our object localization scheme outperforms existing proposal methods in both precision and recall for small number of subwindow proposals (e.g., on ILSVRC-2012 it produces a relative gain of 23.4% over the state-of-the-art for top-1 hypothesis). Furthermore, our experiments show that the annotations automatically-generated by our method can be used to train object detectors yielding recognition results remarkably close to those obtained by training on manually-annotated bounding boxes.

Ha Quang Minh, Loris Bazzani, Vittorio Murino

This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) framework for the problem of learning an unknown functional dependency between a structured input space and a structured output space. Our formulation encompasses both Vector-valued Manifold Regularization and Co-regularized Multi-view Learning, providing in particular a unifying framework linking these two important learning approaches. In the case of the least square loss function, we provide a closed form solution, which is obtained by solving a system of linear equations. In the case of Support Vector Machine (SVM) classification, our formulation generalizes in particular both the binary Laplacian SVM to the multi-class, multi-view settings and the multi-class Simplex Cone SVM to the semi-supervised, multi-view settings. The solution is obtained by solving a single quadratic optimization problem, as in standard SVM, via the Sequential Minimal Optimization (SMO) approach. Empirical results obtained on the task of object recognition, using several challenging datasets, demonstrate the competitiveness of our algorithms compared with other state-of-the-art methods.