75 accepted papers
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, DoRA, and HiRA, enable lightweight adaptation of large pre-trained models via low-rank updates. However, existing PEFT approaches apply static, input-agnostic updates to all tokens, disregarding the varying importance and difficulty of d
While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominantly focus on models without safety alignment. This critical oversight ignores the fact that real-world MLLMs inherently require such mechanisms to mitig
Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural videos often entail. Recent works tackle this problem by al…
Vision-language models (VLMs) have demonstrated remarkable generalization across diverse tasks by leveraging large-scale image-text pretraining. However, their performance is notoriously unstable under variations in natural language prompts, posing a considerable challenge for reliable real-world de…
We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous transport dynamics. Our method adapts Variational Flow Matching to vector-quantized latents by learning categorical posteri…
Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine understanding across multiple visual contexts. To address this limitation, we introduce a new multi-r…
We introduce GateSkip, a simple residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs. Each Attention/MLP branch is equipped with a sigmoid-linear gate that compresses the branch’s output before it re-enters the residual stream. During inference we rank tokens b…
This work does not introduce a new method. Instead, we present an interesting finding that questions the necessity of the inductive bias of locality in modern computer vision architectures. Concretely, we find that vanilla Transformers can operate by directly treating each individual pixel as a toke…
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term strategic and cooperative planning, leading to r…
This paper proposes the first video-grounded entailment tree reasoning method for commonsense video question answering (VQA). Despite the remarkable progress of large visual-language models (VLMs), there are growing concerns that they learn spurious correlations between videos and likely answers, re…
Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt colla…
Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deployment choices under real-world constraints. We introduce SnapViT: single-shot network approximation for pruned Vision Transformers, a new post-pretraining…
Dense self-supervised learning has shown great promise for learning pixel- and patch-level representations, but extending it to videos remains challenging due to the complexity of motion dynamics. Existing approaches struggle as they rely on static augmentations that fail under object deformations,…
What can we learn from comparing video models to human brains, arguably the most efficient and effective video processing systems in existence? Our work takes a step towards answering this question by performing the first large-scale benchmarking of deep video models on representational alignment to…
We address the challenge of representing long captions in vision-language models, such as CLIP. By design these models are limited by fixed, absolute positional encodings, restricting inputs to a maximum of 77 tokens and hindering performance on tasks requiring longer descriptions. Although recent w…
Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Multimodal Large Language Models (MLLMs) struggle at this task. In this paper, we introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding abil…
We study the connection between audio-visual observations and the underlying physics of a mundane yet intriguing everyday activity: pouring liquids. Given only the sound of liquid pouring into a container, our objective is to automatically infer physical properties such as the liquid level, the shap…
This paper revisits the problem of predicting box locations in object detection architectures. Typically, each box proposal or box query aims to directly maximize the intersection-over-union score with the ground truth, followed by a winner-takes-all non-maximum suppression where only the highest sc…
Image-language models with prompt learning have shown remarkable advances in numerous downstream vision tasks. Nevertheless conventional prompt learning methods overfit the training distribution and lose the generalization ability on the test distributions. To improve the generalization across vario…
Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However, existing approaches either overlook the inherent permutation…
Pre-trained vision-language models like CLIP have remarkably adapted to various downstream tasks. Nonetheless, their performance heavily depends on the specificity of the input text prompts, which requires skillful prompt template engineering. Instead, current approaches to prompt optimization learn…
Low-resource settings are well-established in natural lan- guage processing where many languages lack sufficient data for deep learning at scale. However low-resource problems are under-explored in computer vision. In this paper we address this gap and explore the challenges of low-resource image ta…
Vision-Language Models (VLMs) such as Flamingo and GPT-4V have shown immense potential by integrating large language models with vision systems. Nevertheless these models face challenges in the fundamental computer vision task of object localisation due to their training on multimodal data containin…
In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked region autoencoding to learn from groups of pixels or regions. Specifically, we des…
The goal of this paper is to detect objects by exploiting their interrelationships. Contrary to existing methods, which learn objects and relations separately, our key idea is to learn the object-relation distribution jointly. We first propose a novel way of creating a graphical representation of an…
In this paper, we propose energy-based sample adaptation at test time for domain generalization. Where previous works adapt their models to target domains, we adapt the unseen target samples to source-trained models. To this end, we design a discriminative energy-based model, which is trained on sou…
We aim for image-based novelty detection. Despite considerable progress, existing models either fail or face dramatic drop under the so-called ``near-distribution" setup, where the differences between normal and anomalous samples are subtle. We first demonstrate existing methods could experience up…
In the quest for unveiling novel categories at test time, we confront the inherent limitations of traditional supervised recognition models that are restricted by a predefined category set. While strides have been made in the realms of self-supervised and open-world learning towards test-time catego…
Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive for generalization to unseen modality combinations during inf…
Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for few-shot learning with fewer tasks, which we call MetaModulation.…
Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with consistency regularization are commonly adopted to make the model less sensitive…
Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile process. To overcome this limitation, we introduce ProtoDif…
Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process. However, guidance requires a large amount of image-annotation pairs for training and is thus dependent on their availability and correctness. In thi…
In this paper we address the task of finding representative subsets of points in a 3D point cloud by means of a point-wise ordering. Only a few works have tried to address this challenging vision problem, all with the help of hard to obtain point and cloud labels. Different from these works, we intr…
Modern image classifiers perform well on populated classes while degrading considerably on tail classes with only a few instances. Humans, by contrast, effortlessly handle the long-tailed recognition challenge, since they can learn the tail representation based on different levels of semantic abstra…
Modelling and understanding time remains a challenge in contemporary video understanding models. With language emerging as a key driver towards powerful generalization, it is imperative for foundational video-language models to have a sense of time. In this paper, we consider a specific aspect of te…
We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn similarities between videos with identical local motion dynamics but…
Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to handle videos with a dynamic number of objects because it cannot break ties. To overcome this limitation, we first establish a connection between slot attention a…
In this paper, we focus on multi-task classification, where related classification tasks share the same label space and are learned simultaneously. In particular, we tackle a new setting, which is more realistic than currently addressed in the literature, where categories shift from training to test…
This paper strives for activity recognition under domain shift, for example caused by change of scenery or camera viewpoint. The leading approaches reduce the shift in activity appearance by adversarial training and self-supervised learning. Different from these vision-focused works we leverage acti…
In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves the learning capability of transformers for several vision tasks. Specifically, we present BoxeR, short for Box Transfo…
Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and test distributions. Rather than relying on a flat memory, we p…
We aim to understand how actions are performed and identify subtle differences, such as 'fold firmly' vs. 'fold gently'. To this end, we propose a method which recognizes adverbs across different actions. However, such fine-grained annotations are difficult to obtain and their long-tailed nature mak…
"Despite the recent success of video self-supervised learning models, there is much still to be understood about their generalization capability. In this paper, we investigate how sensitive video self-supervised learning is to the current conventional benchmark and whether methods generalize beyond…
We strive to learn a model from a set of source domains that generalizes well to unseen target domains. The main challenge in such a domain generalization scenario is the unavailability of any target domain data during training, resulting in the learned model not being explicitly adapted to the unse…
"The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially true as the level of details in spatio-temporal video unders…
Most set prediction models in deep learning use set-equivariant operations, but they actually operate on multisets. We show that set-equivariant functions cannot represent certain functions on multisets, so we introduce the more appropriate notion of multiset-equivariance. We identify that the exist…
We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in video by simulta…
We aim for source-free domain adaptation, where the task is to deploy a model pre-trained on source domains to target domains. The challenges stem from the distribution shift from the source to the target domain, coupled with the unavailability of any source data and labeled target data for optimiza…
This paper introduces the task of few-shot common action localization in time and space. Given a few trimmed support videos containing the same but unknown action, we strive for spatio-temporal localization of that action in a long untrimmed query video. We do not require any class labels, interval…
Pooling is a critical operation in convolutional neural networks for increasing receptive fields and improving robustness to input variations. Most existing pooling operations downsample the feature maps, which is a lossy process. Moreover, they are not invertible: upsampling a downscaled feature…
Batch normalization plays a crucial role when training deep neural networks. However, batch statistics become unstable with small batch sizes and are unreliable in the presence of distribution shifts. We propose MetaNorm, a simple yet effective meta-learning normalization. It tackles the aforementio…
The goal of this paper is to self-train a 3D convolutional neural network on an unlabeled video collection for deployment on small-scale video collections. As smaller video datasets benefit more from motion than appearance, we strive to train our network using optical flow, but avoid its computation…
This paper strives for repetitive activity counting in videos. Different from existing works, which all analyze the visual video content only, we incorporate for the first time the corresponding sound into the repetition counting process. This benefits accuracy in challenging vision conditions such…
Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space over sets. We focus on stochastic and underdefined cases, where an incorrectly chosen loss function leads to impla…
This paper strives to classify and detect the relationship between object tubelets appearing within a video as a <subject-predicate-object> triplet. Where existing works treat object proposals or tubelets as single entities and model their relations a posteriori, we propose to classify and detect pr…
This paper tackles the problem of localizing actions in long untrimmed videos. Different from existing works, which all use annotated untrimmed videos during training, we learn only from short trimmed videos. This enables learning from large-scale datasets originally designed for action classificati…
This paper strives to recognize individual actions and group activities from videos. While existing solutions for this challenging problem explicitly model spatial and temporal relationships based on location of individual actors, we propose an actor-transformer model able to learn and selectively e…
For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior. Nevertheless, measuring physical properties from visual observations is challenging due to the high number of causally underlying physical parameters -- including material properties and e…
Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative Adversarial Networks that synthesize unseen class features…
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. In this paper, we address both problems. We introduce a probabilistic meta-learning model for domain generalization, in which classifier parameters shared across do…
This paper strives to localize the temporal extent of an action in a long untrimmed video. Where existing work leverages many examples with their start, their ending, and/or the class of the action during training time, we propose few-shot common action localization. The start and end of an action i…
This paper introduces data augmentation for point clouds by interpolation between examples. Data augmentation by interpolation has shown to be a simple and effective approach in the image domain. Such a mixup is however not directly transferable to point clouds, as we do not have a one-to-one corres…
In this paper, we introduce hierarchical action search. Starting from the observation that hierarchies are mostly ignored in the action literature, we retrieve not only individual actions but also relevant and related actions, given an action name or video example as input. We propose a hyperbolic a…
This paper aims to count arbitrary objects in images. The leading counting approaches start from point annotations per object from which they construct density maps. Then, their training objective transforms input images to density maps through deep convolutional networks. We posit that the point an…
The goal of this paper is to detect the spatio-temporal extent of an action. The two-stream detection network based on RGB and flow provides state-of-the-art accuracy at the expense of a large model-size and heavy computation. We propose to embed RGB and optical-flow into a single two-in-one stream…
Few-shot learning is a nascent research topic, motivated by the fact that traditional deep learning requires tremendous amounts of data. In this work, we propose a new task along this research direction, we call few-shot common-localization. Given a few weakly-supervised support images, we aim to lo…
Many computer vision challenges require continuous outputs, but tend to be solved by discrete classification. The reason is classification's natural containment within a probability n-simplex, as defined by the popular softmax activation function. Regular regression lacks such a closed geometry, lea…
This paper strives for pixel-level segmentation of actors and their actions in video content. Different from existing works, which all learn to segment from a fixed vocabulary of actor and action pairs, we infer the segmentation from a natural language input sentence. This allows to distinguish betw…
We consider the problem of estimating repetition in video, such as performing push-ups, cutting a melon or playing violin. Existing work shows good results under the assumption of static and stationary periodicity. As realistic video is rarely perfectly static and stationary, the often preferred Fou…
We aim for zero-shot localization and classification of human actions in video. Where traditional approaches rely on global attribute or object classification scores for their zero-shot knowledge transfer, our main contribution is a spatial-aware object embedding. To arrive at spatial awareness, we…
This paper strives to track a target object in a video. Rather than specifying the target in the first frame of a video by a bounding box, we propose to track the object based on a natural language specification of the target, which provides a more natural human-machine interaction as well as a mean…
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context of image classification. We frame this quest as an active…
The goal of this paper is to recognize actions in video without the need for examples. Different from traditional zero-shot approaches we do not demand the design and specification of attribute classifiers and class-to-attribute mappings to allow for transfer from seen classes to unseen classes. Our…
This paper contributes to automatic classification and localization of human actions in video. Whereas motion is the key ingredient in modern approaches, we assess the benefits of having objects in the video representation. Rather than considering a handful of carefully selected and localized object…