In this paper, we observe that a straight bipartite matching loss can be applied to the output tokens of a vision transformer. This results in a backbone + MLP architecture that can do both tasks without the need of an extra encoder-decoder head and learnable queries. We show that a single MViTv2-S architecture trained with bipartite matching to perform both tasks surpasses the same MViTv2-S when trained with RoI align on pre-computed bounding boxes. With a careful design of token pooling and the proposed training pipeline, our Bipartite-Matching Vision Transformer model, BMViT, achieves +3 mAP on AVA2.2. w.r.t. the two-stage MViTv2-S counterpart. Code is available at https://github.com/IoannaNti/BMViT Action Localization is a challenging problem that combines detection and recognition tasks, which are often addressed separately. State-of-the-art methods rely on off-the-shelf bounding box detections pre-computed at high resolution, and propose transformer models that focus on the classification task alone. Such two-stage solutions are prohibitive for real-time deployment. On the other hand, single-stage methods target both tasks by devoting part of the network (generally the backbone) to sharing the majority of the work-load, compromising performance for speed. These methods build on adding a DETR head with learnable queries that after cross-and self-attention can be sent to corresponding MLPs for detecting a person's bounding box and action. However, DETR-like architectures are challenging to train and can incur in big complexity.

This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting of past and future video features which are then integrated into standard (short-term) video recognition backbones through the use of attention mechanisms. Two well-known problems related to this approach are the quadratic complexity of the attention operation and the fact that the whole feature bank must be stored in memory for inference. To address both issues, we propose an alternative to attention-based schemes which is based on a low-rank approximation of the memory obtained using Singular Value Decomposition. Our scheme has two advantages: (a) it reduces complexity by more than an order of magnitude, and (b) it is amenable to an efficient implementation for the calculation of the memory bases in an incremental fashion which does not require the storage of the whole feature bank in memory. The proposed scheme matches or surpasses the accuracy achieved by attention-based mechanisms while being memory-efficient. Through extensive experiments, we demonstrate that our framework generalises to different architectures and tasks, outperforming the state-of-the-art in three datasets.

This paper sets out to solve the following problem: How can we turn a generative video captioning model into an open-world video/action classification model? Video captioning models can naturally produce open-ended free-form descriptions of a given video which, however, might not be discriminative enough for video/action recognition. Unfortunately, when fine-tuned to auto-regress the class names directly, video captioning models overfit the base classes losing their open-world zero-shot capabilities. To alleviate base class overfitting, in this work, we propose to use reinforcement learning to enforce the output of the video captioning model to be more class-level discriminative. Specifically, we propose ReGen, a novel reinforcement learning based framework with a three-fold objective and reward functions: (1) a class-level discrimination reward that enforces the generated caption to be correctly classified into the corresponding action class, (2) a CLIP reward that encourages the generated caption to continue to be descriptive of the input video (i.e. video-specific), and (3) a grammar reward that preserves the grammatical correctness of the caption. We show that ReGen can train a model to produce captions that are: discriminative, video-specific and grammatically correct. Importantly, when evaluated on standard benchmarks for zero- and few-shot action classification, ReGen significantly outperforms the previous state-of-the-art.

Foundational image-language models have generated considerable interest due to their efficient adaptation to downstream tasks by prompt learning. Prompt learning treats part of the language model input as trainable while freezing the rest, and optimizes an Empirical Risk Mini-mization objective. However, Empirical Risk Minimization is known to suffer from distributional shifts which hurt gen-eralizability to prompts unseen during training. By leveraging the regularization ability of Bayesian methods, we frame prompt learning from the Bayesian perspective and formulate it as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. Our framework is implemented by modeling the input prompt space in a probabilistic manner, as an a priori distribution which makes our proposal compatible with prompt learning approaches that are unconditional or conditional on the image. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space, prevents learning spurious features, and exploits transferable invariant features. This results in better generalization of unseen prompts, even across different datasets and domains.Code available at: https://github.com/saic-fi/Bayesian-Prompt-Learning

Temporal context is key to the recognition of expressions of emotion. Existing methods, that rely on recurrent or self-attention models to enforce temporal consistency, work on the feature level, ignoring the task-specific temporal dependencies, and fail to model context uncertainty. To alleviate these issues, we build upon the framework of Neural Processes to propose a method for apparent emotion recognition with three key novel components: (a) probabilistic contextual representation with a global latent variable model; (b) temporal context modelling using task-specific predictions in addition to features; and (c) smart temporal context selection. We validate our approach on four databases, two for Valence and Arousal estimation (SEWA and AffWild2), and two for Action Unit intensity estimation (DISFA and BP4D). Results show a consistent improvement over a series of strong baselines as well as over state-of-the-art methods.

This paper addresses a major flaw of the cycle consistency loss when used to preserve the input appearance in the face-to-face synthesis domain. In particular, we show that the images generated by a network trained using this loss conceal a noise that hinders their use for further tasks. To overcome this limitation, we propose a “recurrent cycle consistency loss” which for different sequences of target attributes minimises the distance between the output images, independent of any intermediate step. We empirically validate not only that our loss enables the re-use of generated images, but that it also improves their quality. In addition, we propose the very first network that covers the task of unconstrained landmark-guided face-to-face synthesis. Contrary to previous works, our proposed approach enables the transfer of a particular set of input features to a large span of poses and expressions, whereby the target landmarks become the ground-truth points. We then evaluate the consistency of our proposed approach to synthesise faces at the target landmarks. To the best of our knowledge, we are the first to propose a loss to overcome the limitation of the cycle consistency loss, and the first to propose an “in-the-wild” landmark guided synthesis approach.

Facial actions are spatio-temporal signals by nature, and therefore their modeling is crucially dependent on the availability of temporal information. In this paper, we focus on inferring such temporal dynamics of facial actions when no explicit temporal information is available, i.e. from still images. We present a novel self-supervised learning approach to capture multiple scales of temporal dynamics, with an application to facial Action Unit (AU) intensity estimation and dimensional affect estimation. In particular: 1. We propose a framework that infers a dynamic representation (DR) from a still image, capturing the bi-directional flow of time within a short time-window centered at the input image; 2. We show that the proposed rank loss can apply facial temporal evolution to self-supervise the training process without using target representations, allowing the network to represent dynamics more broadly; 3. We propose a multiple temporal scale approach that infers DRs for different window lengths (MDR) from a still image. We empirically validate the value of our approach on the task of frame ranking, and show how our proposed MDR attains state of the art results on BP4D for AU intensity estimation and on SEMAINE for dimensional affect estimation, using only still images at test time.

This paper addresses the problem of unsupervised discovery of object landmarks. We take a different path compared to that of existing works, based on 2 novel perspectives: (1) Self-training: starting from generic keypoints, we propose a self-training approach where the goal is to learn a detector that improves itself becoming more and more tuned to object landmarks. (2) Correspondence: we identify correspondence as a key objective for unsupervised landmark discovery and propose an optimization scheme which alternates between recovering object landmark correspondence across different images via clustering and learning an object landmark descriptor without labels. Compared to previous works, our approach can learn landmarks that are more flexible in terms of capturing large changes in viewpoint. We show the favourable properties of our method on a variety of difficult datasets including LS3D, BBCPose and Human3.6M. Code is available at https://github.com/malldimi1/UnsupervisedLandmarks

This paper proposes a method to ease the unsupervised learning of object landmark detectors. Similarly to previous methods, our approach is fully unsupervised in a sense that it does not require or make any use of annotated landmarks for the target object category. Contrary to previous works, we do however assume that a landmark detector, which has already learned a structured representation for a given object category in a fully supervised manner, is available. Under this setting, our main idea boils down to adapting the given pre-trained network to the target object categories in a fully unsupervised manner. To this end, our method uses the pre-trained network as a core which remains frozen and does not get updated during training, and learns, in an unsupervised manner, only a projection matrix to perform the adaptation to the target categories. By building upon an existing structured representation learned in a supervised manner, the optimization problem solved by our method is much more constrained with significantly less parameters to learn which seems to be important for the case of unsupervised learning. We show that our method surpasses fully unsupervised techniques trained from scratch as well as a strong baseline based on fine-tuning, and produces state-of-the-art results on several datasets. Code can be found at tiny.cc/GitHub-Unsupervised