Data Collection-free Masked Video Modeling

Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the promising ways to solve these issues, yet pre-training solely on synthetic data has its own challenges. In this paper, we introduce an effective self-supervised learning framework for videos that leverages readily available and less costly static images. Specifically, we define the Pseudo Motion Generator (PMG) module that recursively applies image transformations to generate pseudo-motion videos from images. These pseudo-motion videos are then leveraged in masked video modeling. Our approach is applicable to synthetic images as well, thus entirely freeing video pre-training from data collection costs and other concerns in real data. Through experiments in action recognition tasks, we demonstrate that this framework allows effective learning of spatio-temporal features through pseudo-motion videos, significantly improving over existing methods which also use static images and partially outperforming those using both real and synthetic videos. These results uncover fragments of what video transformers learn through masked video modeling.

Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network

Human activities recognition is an important task for an intelligent robot, especially in the field of human-robot collaboration, it requires not only the label of sub-activities but also the temporal structure of the activity. In order to automatically recognize both the label and the temporal structure in sequence of human-object interaction, we propose a novel Pyramid Graph Convolutional Network (PGCN), which employs a pyramidal encoder-decoder architecture consisting of an attention based graph convolution network and a temporal pyramid pooling module for downsampling and upsampling interaction sequence on the temporal axis, respectively. The system represents the 2D or 3D spatial relation of human and objects from the detection results in video data as a graph. To learn the human-object relations, a new attention graph convolutional network is trained to extract condensed information from the graph representation. To segment action into sub-actions, a novel temporal pyramid pooling module is proposed, which upsamples compressed features back to the original time scale and classifies actions per frame. We explore various attention layers, namely spatial attention, temporal attention and channel attention, and combine different upsampling decoders to test the performance on action recognition and segmentation. We evaluate our model on two challenging datasets in the field of human-object interaction recognition, i.e. Bimanual Actions and IKEA Assembly datasets. We demonstrate that our classifier significantly improves both framewise action recognition and segmentation, e.g., F1 micro and F1@50 scores on Bimanual Actions dataset are improved by $4.3\%$ and $8.5\%$ respectively.

Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation

Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each dedicated to processing one modality. Our observations indicate that the network processing intra-frames tend to converge to a flatter minimum than the network processing residuals, which in turn converges to a flatter minimum than the motion vector network. This hierarchy in convergence motivates our strategy for knowledge transfer among modalities to achieve flatter minima, which are generally associated with better generalization. With this insight, we propose Progressive Knowledge Distillation (PKD), a technique that incrementally transfers knowledge across the modalities. This method involves attaching early exits (Internal Classifiers - ICs) to the three networks. PKD distills knowledge starting from the motion vector network, followed by the residual, and finally, the intra-frame network, sequentially improving IC accuracy. Further, we propose the Weighted Inference with Scaled Ensemble (WISE), which combines outputs from the ICs using learned weights, boosting accuracy during inference. Our experiments demonstrate the effectiveness of training the ICs with PKD compared to standard cross-entropy-based training, showing IC accuracy improvements of up to 5.87% and 11.42% on the UCF-101 and HMDB-51 datasets, respectively. Additionally, WISE improves accuracy by up to 4.28% and 9.30% on UCF-101 and HMDB-51, respectively.

ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition

Our world is full of varied actions and moves across specialized domains that we, as humans, strive to identify and understand. Within any single domain, actions can often appear quite similar, making it challenging for deep models to distinguish them accurately. To evaluate the effectiveness of multimodal foundation models in helping us recognize such actions, we present ActionAtlas v1.0, a multiple-choice video question answering benchmark featuring short videos across various sports. Each video in the dataset is paired with a question and four or five choices. The question pinpoints specific individuals, asking which choice "best" describes their action within a certain temporal context. Overall, the dataset includes 934 videos showcasing 580 unique actions across 56 sports, with a total of 1896 actions within choices. Unlike most existing video question answering benchmarks that only cover simplistic actions, often identifiable from a single frame, ActionAtlas focuses on intricate movements and rigorously tests the model's capability to discern subtle differences between moves that look similar within each domain. We evaluate open and proprietary foundation models on this benchmark, finding that the best model, GPT-4o, achieves a maximum accuracy of 45.52%. Meanwhile, Non-expert crowd workers, provided with action description for each choice, achieve 61.64% accuracy, where random chance is approximately 21%. Our findings with state-of-the-art models indicate that having a high frame sampling rate is important for accurately recognizing actions in ActionAtlas, a feature that some leading proprietary video models, such as Gemini, do not include in their default configuration.

Scaling Wearable Foundation Models

Wearable sensors have become ubiquitous thanks to a variety of health tracking features. The resulting continuous and longitudinal measurements from everyday life generate large volumes of data; however, making sense of these observations for scientific and actionable insights is non-trivial. Inspired by the empirical success of generative modeling, where large neural networks learn powerful representations from vast amounts of text, image, video, or audio data, we investigate the scaling properties of sensor foundation models across compute, data, and model size. Using a dataset of up to 40 million hours of in-situ heart rate, heart rate variability, electrodermal activity, accelerometer, skin temperature, and altimeter per-minute data from over 165,000 people, we create LSM, a multimodal foundation model built on the largest wearable-signals dataset with the most extensive range of sensor modalities to date. Our results establish the scaling laws of LSM for tasks such as imputation, interpolation and extrapolation, both across time and sensor modalities. Moreover, we highlight how LSM enables sample-efficient downstream learning for tasks like exercise and activity recognition.

FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition

Real-life applications of action recognition often require a fine-grained understanding of subtle movements, e.g., in sports analytics, user interactions in AR/VR, and surgical videos. Although fine-grained actions are more costly to annotate, existing semi-supervised action recognition has mainly focused on coarse-grained action recognition. Since fine-grained actions are more challenging due to the absence of scene bias, classifying these actions requires an understanding of action-phases. Hence, existing coarse-grained semi-supervised methods do not work effectively. In this work, we for the first time thoroughly investigate semi-supervised fine-grained action recognition (FGAR). We observe that alignment distances like dynamic time warping (DTW) provide a suitable action-phase-aware measure for comparing fine-grained actions, a concept previously unexploited in FGAR. However, since regular DTW distance is pairwise and assumes strict alignment between pairs, it is not directly suitable for classifying fine-grained actions. To utilize such alignment distances in a limited-label setting, we propose an Alignability-Verification-based Metric learning technique to effectively discriminate between fine-grained action pairs. Our learnable alignability score provides a better phase-aware measure, which we use to refine the pseudo-labels of the primary video encoder. Our collaborative pseudo-labeling-based framework `\textit{FinePseudo}' significantly outperforms prior methods on four fine-grained action recognition datasets: Diving48, FineGym99, FineGym288, and FineDiving, and shows improvement on existing coarse-grained datasets: Kinetics400 and Something-SomethingV2. We also demonstrate the robustness of our collaborative pseudo-labeling in handling novel unlabeled classes in open-world semi-supervised setups. Project Page: https://daveishan.github.io/finepsuedo-webpage/.

Referring Atomic Video Action Recognition

We introduce a new task called Referring Atomic Video Action Recognition (RAVAR), aimed at identifying atomic actions of a particular person based on a textual description and the video data of this person. This task differs from traditional action recognition and localization, where predictions are delivered for all present individuals. In contrast, we focus on recognizing the correct atomic action of a specific individual, guided by text. To explore this task, we present the RefAVA dataset, containing 36,630 instances with manually annotated textual descriptions of the individuals. To establish a strong initial benchmark, we implement and validate baselines from various domains, e.g., atomic action localization, video question answering, and text-video retrieval. Since these existing methods underperform on RAVAR, we introduce RefAtomNet -- a novel cross-stream attention-driven method specialized for the unique challenges of RAVAR: the need to interpret a textual referring expression for the targeted individual, utilize this reference to guide the spatial localization and harvest the prediction of the atomic actions for the referring person. The key ingredients are: (1) a multi-stream architecture that connects video, text, and a new location-semantic stream, and (2) cross-stream agent attention fusion and agent token fusion which amplify the most relevant information across these streams and consistently surpasses standard attention-based fusion on RAVAR. Extensive experiments demonstrate the effectiveness of RefAtomNet and its building blocks for recognizing the action of the described individual. The dataset and code will be made publicly available at https://github.com/KPeng9510/RAVAR.

Pose-guided multi-task video transformer for driver action recognition

We investigate the task of identifying situations of distracted driving through analysis of in-car videos. To tackle this challenge we introduce a multi-task video transformer that predicts both distracted actions and driver pose. Leveraging VideoMAEv2, a large pre-trained architecture, our approach incorporates semantic information from human keypoint locations to enhance action recognition and decrease computational overhead by minimizing the number of spatio-temporal tokens. By guiding token selection with pose and class information, we notably reduce the model's computational requirements while preserving the baseline accuracy. Our model surpasses existing state-of-the art results in driver action recognition while exhibiting superior efficiency compared to current video transformer-based approaches.

ToddlerAct: A Toddler Action Recognition Dataset for Gross Motor Development Assessment

Assessing gross motor development in toddlers is crucial for understanding their physical development and identifying potential developmental delays or disorders. However, existing datasets for action recognition primarily focus on adults, lacking the diversity and specificity required for accurate assessment in toddlers. In this paper, we present ToddlerAct, a toddler gross motor action recognition dataset, aiming to facilitate research in early childhood development. The dataset consists of video recordings capturing a variety of gross motor activities commonly observed in toddlers aged under three years old. We describe the data collection process, annotation methodology, and dataset characteristics. Furthermore, we benchmarked multiple state-of-the-art methods including image-based and skeleton-based action recognition methods on our datasets. Our findings highlight the importance of domain-specific datasets for accurate assessment of gross motor development in toddlers and lay the foundation for future research in this critical area. Our dataset will be available at https://github.com/ipl-uw/ToddlerAct.

SoccerNet 2024 Challenges Results

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.