Most existing object detection methods rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements substantially limit their scalability to open-ended accommodation of novel classes with limited labelled training data. We present a study aiming to go beyond these limitations by considering the Incremental Few-Shot Detection (iFSD) problem setting, where new classes must be registered incrementally (without revisiting base classes) and with few examples. To this end we propose OpeNended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples. This is achieved by an elegant adaptation of the CentreNet detector to the few-shot learning scenario, and meta-learning a class-specific code generator model for registering novel classes. ONCE fully respects the incremental learning paradigm, with novel class registration requiring only a single forward pass of few-shot training samples, and no access to base classes -thus making it suitable for deployment on embedded devices. Extensive experiments conducted on both the standard object detection and fashion landmark detection tasks show the feasibility of iFSD for the first time, opening an interesting and very important line of research.

We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion architectures. In order to find an optimal architecture for a given dataset in the proposed search space, we leverage an efficient sequential model-based exploration approach that is tailored for the problem. We demonstrate the value of posing multimodal fusion as a neural architecture search problem by extensive experimentation on a toy dataset and two other real multimodal datasets. We discover fusion architectures that exhibit state-of-the-art performance for problems with different domain and dataset size, including the NTU RGB+D dataset, the largest multimodal action recognition dataset available.

Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we propose to study the video activity localization problem from a denoising perspective. Specifically, we propose an encoder-decoder model named DenoiseLoc. During training, a set of action spans is randomly generated from the ground truth with a controlled noise scale. Then we attempt to reverse this process by boundary denoising, allowing the localizer to predict activities with precise boundaries and resulting in faster convergence speed. Experiments show that DenoiseLoc advances several video activity understanding tasks. For example, we observe a gain of +12.36% average mAP on QV-Highlights dataset and +1.64%

Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode, the few samples in a meta-training task are split into support and query sets. The former is used to build a classifier, which is then evaluated on the latter using a query-centered loss for model updating. There are however two major limitations: lack of data efficiency due to the query-centered only loss design and inability to deal with the support set outlying samples and inter-class distribution overlapping problems. In this paper, we overcome both limitations by proposing a new Prototype-centered Attentive Learning (PAL) model composed of two novel components. First, a prototype-centered contrastive learning loss is introduced to complement the conventional querycentered learning objective, in order to make full use of the limited training samples in each episode. Second, PAL further integrates a hybrid attentive learning mechanism that can minimize the negative impacts of outliers and promote class separation. Extensive experiments on four standard few-shot action benchmarks show that our method clearly outperforms previous state-of-the-art methods, with the improvement particularly significant (> 10%) on the most challenging fine-grained action recognition benchmark.

The problem of localizing occlusions between consecutive frames of a video is important but rarely tackled on its own. In most works, it is tightly interleaved with the computation of accurate optical flows, which leads to a delicate chicken-and-egg problem. With this in mind, we propose a novel approach to occlusion detection where visibility or not of a point in next frame is formulated in terms of visual reconstruction. The key issue is now to determine how well a pixel in the first image can be "reconstructed" from co-located colors in the next image. We first exploit this reasoning at the pixel level with a new detection criterion. Contrary to the ubiquitous displaced-framedifference and forward-backward flow vector matching, the proposed alternative does not critically depend on a precomputed, dense displacement field, while being shown to be more effective. We then leverage this local modeling within an energy-minimization framework that delivers occlusion maps. An easy-to-obtain collection of parametric motion models is exploited within the energy to provide the required level of motion information. Our approach outperforms state-of-the-art detection methods on the challenging MPI Sintel dataset.

No abstract

Attentive video modeling is essential for action recognition in unconstrained videos due to their rich yet redundant information over space and time. However, introducing attention in a deep neural network for action recognition is challenging for two reasons. First, an effective attention module needs to learn what (objects and their local motion patterns), where (spatially), and when (temporally) to focus on. Second, a video attention module must be efficient because existing action recognition models already suffer from high computational cost. To address both challenges, a novel What-Where-When (W3) video attention module is proposed. Departing from existing alternatives, our W3 module models all three facets of video attention jointly. Crucially, it is extremely efficient by factorizing the high-dimensional video feature data into lowdimensional meaningful spaces (1D channel vector for 'what' and 2D spatial tensors for 'where'), followed by lightweight temporal attention reasoning. Extensive experiments show that our attention model brings significant improvements to existing action recognition models, achieving new state-of-the-art performance on a number of benchmarks.

No abstract