Growing amount of different practical tasks in a video understanding problem has addressed the great challenge aiming to design an universal solution, which should be available for broad masses and suitable for the demanding edge-oriented inference. In this paper we are focused on designing a network architecture and a training pipeline to tackle the mentioned challenges. Our architecture takes the best from the previous ones and brings the ability to be successful not only in appearance-based action recognition tasks but in motion-based problems too. Furthermore, the induced label noise problem is formulated and Adaptive Clip Selection (ACS) framework is proposed to deal with it. Together it makes the LIGAR framework the general-purpose action recognition solution. We also have reported the extensive analysis on the general and gesture datasets to show the excellent trade-off between the performance and the accuracy in comparison to the state-of-the-art solutions. Training code is available at: https://github.com/openvinotoolkit/training_extensions. For the efficient edge-oriented inference all trained models can be exported into the OpenVINO format.
Action detection plays an important role in high-level video understanding and media interpretation. Many existing studies fulfill this spatio-temporal localization by modeling the context, capturing the relationship of actors, objects, and scenes conveyed in the video. However, they often universally treat all the actors without considering the consistency and distinctness between individuals, leaving much room for improvement. In this paper, we explicitly highlight the identity information of the actors in terms of both long-term and short-term context through a graph memory network, namely identity-aware graph memory network (IGMN). Specifically, we propose the hierarchical graph neural network (HGNN) to comprehensively conduct long-term relation modeling within the same identity as well as between different ones. Regarding short-term context, we develop a dual attention module (DAM) to generate identity-aware constraint to reduce the influence of interference by the actors of different identities. Extensive experiments on the challenging AVA dataset demonstrate the effectiveness of our method, which achieves state-of-the-art results on AVA v2.1 and v2.2.
As a challenging task of high-level video understanding, weakly supervised temporal action localization has been attracting increasing attention. With only video annotations, most existing methods seek to handle this task with a localization-by-classification framework, which generally adopts a selector to select snippets of high probabilities of actions or namely the foreground. Nevertheless, the existing foreground selection strategies have a major limitation of only considering the unilateral relation from foreground to actions, which cannot guarantee the foreground-action consistency. In this paper, we present a framework named FAC-Net based on the I3D backbone, on which three branches are appended, named class-wise foreground classification branch, class-agnostic attention branch and multiple instance learning branch. First, our class-wise foreground classification branch regularizes the relation between actions and foreground to maximize the foreground-background separation. Besides, the class-agnostic attention branch and multiple instance learning branch are adopted to regularize the foreground-action consistency and help to learn a meaningful foreground classifier. Within each branch, we introduce a hybrid attention mechanism, which calculates multiple attention scores for each snippet, to focus on both discriminative and less-discriminative snippets to capture the full action boundaries. Experimental results on THUMOS14 and ActivityNet1.3 demonstrate the state-of-the-art performance of our method. Our code is available at https://github.com/LeonHLJ/FAC-Net.
Action recognition is an important task for video understanding with broad applications. However, developing an effective action recognition solution often requires extensive engineering efforts in building and testing different combinations of the modules and their hyperparameters. In this demo, we present AutoVideo, a Python system for automated video action recognition. AutoVideo is featured for 1) highly modular and extendable infrastructure following the standard pipeline language, 2) an exhaustive list of primitives for pipeline construction, 3) data-driven tuners to save the efforts of pipeline tuning, and 4) easy-to-use Graphical User Interface (GUI). AutoVideo is released under MIT license at https://github.com/datamllab/autovideo
In video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed videos. However, action detection requires not only categorizing actions, but also localizing them in untrimmed videos. Therefore, transferring knowledge pertaining to temporal relations is critical for this task which is missing in the previous cross-modal KD frameworks. To this end, we aim at learning an augmented RGB representation for action detection, taking advantage of additional modalities at training time through KD. We propose a KD framework consisting of two levels of distillation. On one hand, atomic-level distillation encourages the RGB student to learn the sub-representation of the actions from the teacher in a contrastive manner. On the other hand, sequence-level distillation encourages the student to learn the temporal knowledge from the teacher, which consists of transferring the Global Contextual Relations and the Action Boundary Saliency. The result is an Augmented-RGB stream that can achieve competitive performance as the two-stream network while using only RGB at inference time. Extensive experimental analysis shows that our proposed distillation framework is generic and outperforms other popular cross-modal distillation methods in action detection task.
The growing number of action classes has posed a new challenge for video understanding, making Zero-Shot Action Recognition (ZSAR) a thriving direction. The ZSAR task aims to recognize target (unseen) actions without training examples by leveraging semantic representations to bridge seen and unseen actions. However, due to the complexity and diversity of actions, it remains challenging to semantically represent action classes and transfer knowledge from seen data. In this work, we propose an ER-enhanced ZSAR model inspired by an effective human memory technique Elaborative Rehearsal (ER), which involves elaborating a new concept and relating it to known concepts. Specifically, we expand each action class as an Elaborative Description (ED) sentence, which is more discriminative than a class name and less costly than manual-defined attributes. Besides directly aligning class semantics with videos, we incorporate objects from the video as Elaborative Concepts (EC) to improve video semantics and generalization from seen actions to unseen actions. Our ER-enhanced ZSAR model achieves state-of-the-art results on three existing benchmarks. Moreover, we propose a new ZSAR evaluation protocol on the Kinetics dataset to overcome limitations of current benchmarks and demonstrate the first case where ZSAR performance is comparable to few-shot learning baselines on this more realistic setting. We will release our codes and collected EDs at https://github.com/DeLightCMU/ElaborativeRehearsal.
Video captioning combines video understanding and language generation. Different from image captioning that describes a static image with details of almost every object, video captioning usually considers a sequence of frames and biases towards focused objects, e.g., the objects that stay in focus regardless of the changing background. Therefore, detecting and properly accommodating focused objects is critical in video captioning. To enforce the description of focused objects and achieve controllable video captioning, we propose an Object-Oriented Non-Autoregressive approach (O2NA), which performs caption generation in three steps: 1) identify the focused objects and predict their locations in the target caption; 2) generate the related attribute words and relation words of these focused objects to form a draft caption; and 3) combine video information to refine the draft caption to a fluent final caption. Since the focused objects are generated and located ahead of other words, it is difficult to apply the word-by-word autoregressive generation process; instead, we adopt a non-autoregressive approach. The experiments on two benchmark datasets, i.e., MSR-VTT and MSVD, demonstrate the effectiveness of O2NA, which achieves results competitive with the state-of-the-arts but with both higher diversity and higher inference speed.
Transformer achieves remarkable successes in understanding 1 and 2-dimensional signals (e.g., NLP and Image Content Understanding). As a potential alternative to convolutional neural networks, it shares merits of strong interpretability, high discriminative power on hyper-scale data, and flexibility in processing varying length inputs. However, its encoders naturally contain computational intensive operations such as pair-wise self-attention, incurring heavy computational burden when being applied on the complex 3-dimensional video signals. This paper presents Token Shift Module (i.e., TokShift), a novel, zero-parameter, zero-FLOPs operator, for modeling temporal relations within each transformer encoder. Specifically, the TokShift barely temporally shifts partial [Class] token features back-and-forth across adjacent frames. Then, we densely plug the module into each encoder of a plain 2D vision transformer for learning 3D video representation. It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding. Experiments on standard benchmarks verify its robustness, effectiveness, and efficiency. Particularly, with input clips of 8/12 frames, the TokShift transformer achieves SOTA precision: 79.83%/80.40% on the Kinetics-400, 66.56% on EGTEA-Gaze+, and 96.80% on UCF-101 datasets, comparable or better than existing SOTA convolutional counterparts. Our code is open-sourced in: https://github.com/VideoNetworks/TokShift-Transformer.
The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization.
Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified. Code available at: https://github.com/yrcong/STTran.
We introduce CogME, a cognition-inspired, multi-dimensional evaluation metric designed for AI models focusing on story understanding. CogME is a framework grounded in human thinking strategies and story elements that involve story understanding. With a specific breakdown of the questions, this approach provides a nuanced assessment revealing not only AI models' particular strengths and weaknesses but also the characteristics of the benchmark dataset. Our case study with the DramaQA dataset demonstrates a refined analysis of the model and the benchmark dataset. We argue the need for metrics based on understanding the nature of tasks and designed to align closely with human cognitive processes. This approach provides insights beyond traditional overall scores and paves the way for more sophisticated AI development targeting higher cognitive functions.
Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss. We first carry out a series of pilot experiments to show disentangling such conjunctions can lead to persistent performance improvement. Then, based on these findings, we propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors. Extensive experiments on MS COCO benchmark show that our approach can lead to 2.0 mAP, 2.4 mAP and 2.2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead. Notably, our best model reaches 55.0 mAP on the COCO test-dev set and 93.5 AP on the hard subset of WIDER FACE, achieving new state-of-the-art performance on these two competitive benchmarks. Code is available at https://github.com/zehuichen123/DDOD.
Research in action detection has grown in the recentyears, as it plays a key role in video understanding. Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task. While recent works use spatial features with aggregated temporal information, this work proposes to use non-aggregated temporal information. This is done by adding an attention based method that leverages spatio-temporal interactions between elements in the scene along the clip.The main contribution of this work is the introduction of two cross attention blocks to effectively model the spatial relations and capture short range temporal interactions.Experiments on the AVA dataset show the advantages of the proposed approach that models spatio-temporal relations between relevant elements in the scene, outperforming other methods that model actor interactions with their context by +0.31 mAP.
We explore a new perspective on video understanding by casting the video recognition problem as an image recognition task. Our approach rearranges input video frames into super images, which allow for training an image classifier directly to fulfill the task of action recognition, in exactly the same way as image classification. With such a simple idea, we show that transformer-based image classifiers alone can suffice for action recognition. In particular, our approach demonstrates strong and promising performance against SOTA methods on several public datasets including Kinetics400, Moments In Time, Something-Something V2 (SSV2), Jester and Diving48. We also experiment with the prevalent ResNet image classifiers in computer vision to further validate our idea. The results on both Kinetics400 and SSV2 are comparable to some of the best-performed CNN approaches based on spatio-temporal modeling. Our source codes and models are available at https://github.com/IBM/sifar-pytorch.
With rapidly evolving internet technologies and emerging tools, sports related videos generated online are increasing at an unprecedentedly fast pace. To automate sports video editing/highlight generation process, a key task is to precisely recognize and locate the events in the long untrimmed videos. In this tech report, we present a two-stage paradigm to detect what and when events happen in soccer broadcast videos. Specifically, we fine-tune multiple action recognition models on soccer data to extract high-level semantic features, and design a transformer based temporal detection module to locate the target events. This approach achieved the state-of-the-art performance in both two tasks, i.e., action spotting and replay grounding, in the SoccerNet-v2 Challenge, under CVPR 2021 ActivityNet workshop. Our soccer embedding features are released at https://github.com/baidu-research/vidpress-sports. By sharing these features with the broader community, we hope to accelerate the research into soccer video understanding.
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video architecture is realized by adapting the Swin Transformer designed for the image domain, while continuing to leverage the power of pre-trained image models. Our approach achieves state-of-the-art accuracy on a broad range of video recognition benchmarks, including on action recognition (84.9 top-1 accuracy on Kinetics-400 and 86.1 top-1 accuracy on Kinetics-600 with ~20x less pre-training data and ~3x smaller model size) and temporal modeling (69.6 top-1 accuracy on Something-Something v2). The code and models will be made publicly available at https://github.com/SwinTransformer/Video-Swin-Transformer.
In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting strategies to obtain visual tokens and processing a large number of densely sampled patches for attention, our approach learns to mine important tokens in visual data. This results in efficiently and effectively finding a few important visual tokens and enables modeling of pairwise attention between such tokens, over a longer temporal horizon for videos, or the spatial content in images. Our experiments demonstrate strong performance on several challenging benchmarks for both image and video recognition tasks. Importantly, due to our tokens being adaptive, we accomplish competitive results at significantly reduced compute amount. We obtain comparable results to the state-of-the-arts on ImageNet while being computationally more efficient. We also confirm the effectiveness of the approach on multiple video datasets, including Kinetics-400, Kinetics-600, Charades, and AViD. The code is available at: https://github.com/google-research/scenic/tree/main/scenic/projects/token_learner
Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In this paper, we study long-form video understanding. We introduce a framework for modeling long-form videos and develop evaluation protocols on large-scale datasets. We show that existing state-of-the-art short-term models are limited for long-form tasks. A novel object-centric transformer-based video recognition architecture performs significantly better on 7 diverse tasks. It also outperforms comparable state-of-the-art on the AVA dataset.
Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task on discretized video tokens generated via VQ-VAE. Unlike language, where the text tokens are more independent, neighboring video tokens typically have strong correlations (e.g., consecutive video frames usually look very similar), and hence uniformly masking individual tokens will make the task too trivial to learn useful representations. To deal with this issue, we propose a block-wise masking strategy where we mask neighboring video tokens in both spatial and temporal domains. We also add an augmentation-free contrastive learning method to further capture the global content by predicting whether the video clips are sampled from the same video. We pre-train our model on uncurated videos and show that our pre-trained model can reach state-of-the-art results on several video understanding datasets (e.g., SSV2, Diving48). Lastly, we provide detailed analyses on model scalability and pre-training method design. Code is released at https://github.com/airsplay/vimpac.
Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.