Large vision-language models revolutionized image classification and semantic segmentation paradigms. However, they typically assume a pre-defined set of categories, or vocabulary, at test time for composing textual prompts. This assumption is impractical in scenarios with unknown or evolving semantic context. Here, we address this issue and introduce the Vocabulary-free Image Classification (VIC) task, which aims to assign a class from an unconstrained language-induced semantic space to an input image without needing a known vocabulary. VIC is challenging due to the vastness of the semantic space, which contains millions of concepts, including fine-grained categories. To address VIC, we propose Category Search from External Databases (CaSED), a training-free method that leverages a pre-trained vision-language model and an external database. CaSED first extracts the set of candidate categories from the most semantically similar captions in the database and then assigns the image to the best-matching candidate category according to the same vision-language model. Furthermore, we demonstrate that CaSED can be applied locally to generate a coarse segmentation mask that classifies image regions, introducing the task of Vocabulary-free Semantic Segmentation. CaSED and its variants outperform other more complex vision-language models, on classification and semantic segmentation benchmarks, while using much fewer parameters.

Attribute detection is crucial for many computer vision tasks, as it enables systems to describe properties such as color, texture, and material. Current approaches often rely on labor-intensive annotation processes which are inherently limited: objects can be described at an arbitrary level of detail (e.g., color vs. color shades), leading to ambiguities when the annotators are not instructed carefully. Furthermore, they operate within a predefined set of attributes, reducing scalability and adaptability to unforeseen downstream applications. We present Compositional Caching (ComCa), a training-free method for open-vocabulary attribute detection that overcomes these constraints. ComCa requires only the list of target attributes and objects as input, using them to populate an auxiliary cache of images by leveraging web-scale databases and Large Language Models to determine attribute-object compatibility. To account for the compositional nature of attributes, cache images receive soft attribute labels. Those are aggregated at inference time based on the similarity between the input and cache images, refining the predictions of underlying Vision-Language Models (VLMs). Importantly, our approach is model-agnostic, compatible with various VLMs. Experiments on public datasets demonstrate that ComCa significantly outperforms zero-shot and cache-based baselines, competing with recent training-based methods, proving that a carefully designed training-free approach can successfully address open-vocabulary attribute detection.

Traditional image classification requires a predefined list of semantic categories. In contrast, Large Multimodal Models (LMMs) can sidestep this requirement by classifying images directly using natural language (e.g., answering the prompt "What is the main object in the image?"). Despite this remarkable capability, most existing studies on LMM classification performance are surprisingly limited in scope, often assuming a closed-world setting with a predefined set of categories. In this work, we address this gap by thoroughly evaluating LMM classification performance in a truly open-world setting. We first formalize the task and introduce an evaluation protocol, defining various metrics to assess the alignment between predicted and ground truth classes. We then evaluate 13 models across 10 benchmarks, encompassing prototypical, non-prototypical, fine-grained, and very fine-grained classes, demonstrating the challenges LMMs face in this task. Further analyses based on the proposed metrics reveal the types of errors LMMs make, highlighting challenges related to granularity and fine-grained capabilities, showing how tailored prompting and reasoning can alleviate them.

Human-Object Interaction (HOI) detection aims to identify humans and objects within images and interpret their interactions. Existing HOI methods rely heavily on large datasets with manual annotations to learn interactions from visual cues. These annotations are labor-intensive to create, prone to inconsistency, and limit scalability to new domains and rare interactions. We argue that recent advances in Vision-Language Models (VLMs) offer untapped potential, particularly in enhancing interaction representation. While prior work has injected such potential and even proposed training-free methods, there remain key gaps. Consequently, we propose a novel training-free HOI detection framework for Dynamic Scoring with enhanced semantics (dysco) that effectively utilizes textual and visual interaction representations within a multimodal registry, enabling robust and nuanced interaction understanding. This registry incorporates a small set of visual cues and uses innovative interaction signatures to improve the semantic alignment of verbs, facilitating effective generalization to rare interactions. Additionally, we propose a unique multi-head attention mechanism that adaptively weights the contributions of the visual and textual features. Experimental results demonstrate that our dysco surpasses training-free state-of-the-art models and is competitive with training-based approaches, particularly excelling in rare interactions. Code is available at https://github.com/francescotonini/dysco.

What does it mean for two videos to be similar? Videos may appear similar when judged by the actions they depict, yet entirely different if evaluated based on the locations where they were filmed. While humans naturally compare videos by taking different aspects into account, this ability has not been thoroughly studied and presents a challenge for models that often depend on broad global similarity scores. Large Multimodal Models (LMMs) with video understanding capabilities open new opportunities for leveraging natural language in comparative video tasks. We introduce Concept-based Video Similarity estimation (ConViS), a novel task that compares pairs of videos by computing interpretable similarity scores across a predefined set of key semantic concepts. ConViS allows for human-like reasoning about video similarity and enables new applications such as concept-conditioned video retrieval. To support this task, we also introduce ConViS-Bench, a new benchmark comprising carefully annotated video pairs spanning multiple domains. Each pair comes with concept-level similarity scores and textual descriptions of both differences and similarities. Additionally, we benchmark several state-of-the-art models on ConViS, providing insights into their alignment with human judgments. Our results reveal significant performance differences on ConViS, indicating that some concepts present greater challenges for estimating video similarity. We believe that ConViS-Bench will serve as a valuable resource for advancing research in language-driven video understanding.

Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model on a large amount of annotated training data. While effective, training-based ZS-TAL approaches assume the availability of labeled data for supervised learning, which can be impractical in some applications. Furthermore, the training process naturally induces a domain bias into the learned model, which may adversely affect the model's generalization ability to arbitrary videos. These considerations prompt us to approach the ZS-TAL problem from a radically novel perspective, relaxing the requirement for training data. To this aim, we introduce a novel method that performs Test-Time adaptation for Temporal Action Localization (T3AL). In a nutshell, T3AL adapts a pre-trained Vision and Language Model (VLM). T3AL operates in three steps. First, a video-level pseudo-label of the action category is computed by aggregating information from the entire video. Then, action localization is performed adopting a novel procedure inspired by self-supervised learning. Finally, frame-level textual descriptions extracted with a state-of-the-art captioning model are employed for refining the action region proposals. We validate the effectiveness of T3AL by conducting experiments on the THUMOS14 and the ActivityNet-v1.3 datasets. Our results demonstrate that T3AL significantly outperforms zero-shot baselines based on state-of-the-art VLMs, confirming the benefit of a test-time adaptation approach.

Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data. The previous approaches have attempted to address SFVUDA by leveraging self-supervision (e.g., enforcing temporal consistency) derived from the target data itself. In this work, we take an orthogonal approach by exploiting "web-supervision" from Large Language-Vision Models (LLVMs), driven by the rationale that LLVMs contain a rich world prior surprisingly robust to domain-shift. We showcase the unreasonable effectiveness of integrating LLVMs for SFVUDA by devising an intuitive and parameter-efficient method, which we name Domain Adaptation with Large Language-Vision models (DALL-V), that distills the world prior and complementary source model information into a student network tailored for the target. Despite the simplicity, DALL-V1achieves significant improvement over state-of-the-art SFVUDA methods.

Recent advances in large vision-language models have revolutionized the image classification paradigm. Despite showing impressive zero-shot capabilities, a pre-defined set of categories, a.k.a. the vocabulary, is assumed at test time for composing the textual prompts. However, such assumption can be impractical when the semantic context is unknown and evolving. We thus formalize a novel task, termed as Vocabulary-free Image Classification (VIC), where we aim to assign to an input image a class that resides in an unconstrained language-induced semantic space, without the prerequisite of a known vocabulary. VIC is a challenging task as the semantic space is extremely large, containing millions of concepts, with hard-to-discriminate fine-grained categories. In this work, we first empirically verify that representing this semantic space by means of an external vision-language database is the most effective way to obtain semantically relevant content for classifying the image. We then propose Category Search from External Databases (CaSED), a method that exploits a pre-trained vision-language model and an external vision-language database to address VIC in a training-free manner. CaSED first extracts a set of candidate categories from captions retrieved from the database based on their semantic similarity to the image, and then assigns to the image the best matching candidate category according to the same vision-language model. Experiments on benchmark datasets validate that CaSED outperforms other complex vision-language frameworks, while being efficient with much fewer parameters, paving the way for future research in this direction.

Emotion recognition is involved in several real-world applications. With an increase in available modalities, automatic understanding of emotions is being performed more accurately. The success in Multimodal Emotion Recognition (MER), primarily relies on the supervised learning paradigm. However, data annotation is expensive, time-consuming, and as emotion expression and perception depends on several factors (e.g., age, gender, culture) obtaining labels with a high reliability is hard. Motivated by these, we focus on unsupervised feature learning for MER. We consider discrete emotions, and as modalities text, audio and vision are used. Our method, as being based on contrastive loss between pairwise modalities, is the first attempt in MER literature. Our end-to-end feature learning approach has several differences (and advantages) compared to existing MER methods: i) it is unsupervised, so the learning is lack of data labelling cost; ii) it does not require data spatial augmentation, modality alignment, large number of batch size or epochs; iii) it applies data fusion only at inference; and iv) it does not require backbones pre-trained on emotion recognition task. The experiments on benchmark datasets show that our method outperforms several baseline approaches and unsupervised learning methods applied in MER. Particularly, it even surpasses a few supervised MER state-of-the-art.