Activity Recognition

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

30 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

11 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 330 papers with code (1,322 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Real-world Anomaly Detection in Surveillance Videos
  12 Jan 2018 9 repositories listed Syntology ran 4 of 6 samples · 2 unverified · 4 pointer-only (licence)
  To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled…
• Multivariate LSTM-FCNs for Time Series Classification
  14 Jan 2018 7 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Over the past decade, multivariate time series classification has received great attention.
• CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
  10 Apr 2022 6 repositories listed
  In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.
• Representation Flow for Action Recognition
  2 Oct 2018 5 repositories listed
  Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition.
• Temporal Relational Reasoning in Videos
  22 Nov 2017 5 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.
• Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
  21 Nov 2022 4 repositories listed
  Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
• Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition
  5 Aug 2019 4 repositories listed
  However, by exploiting a simple technique that removes motion information, we show that it is not the case that this technique is effective as-is for representing relevance in non-image tasks.
• Im2Flow: Motion Hallucination from Static Images for Action Recognition
  12 Dec 2017 4 repositories listed
  Second, we show the power of hallucinated flow for recognition, successfully transferring the learned motion into a standard two-stream network for activity recognition.
• Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
  22 Aug 2017 4 repositories listed
  Human activity recognition (HAR) has become a popular topic in research because of its wide application.
• TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
  30 Mar 2017 4 repositories listed
  We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.
• HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
  17 Nov 2022 3 repositories listed
  The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption.
• SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning
  3 Aug 2020 3 repositories listed Syntology ran 2 of 9 samples · 7 unverified
  In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives.
• Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
  26 Nov 2019 3 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation.
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
  12 May 2019 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition.
• Large-scale weakly-supervised pre-training for video action recognition
  2 May 2019 3 repositories listed Syntology ran 0 of 21 samples · 21 unverified
  Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning?
• Eidetic 3D LSTM: A Model for Video Prediction and Beyond
  1 May 2019 3 repositories listed
  We first evaluate the E3D-LSTM network on widely-used future video prediction datasets and achieve the state-of-the-art performance.
• Fine-grained Activity Recognition in Baseball Videos
  9 Apr 2018 3 repositories listed
  In this paper, we introduce a challenging new dataset, MLB-YouTube, designed for fine-grained activity detection.
• Kernel Cross-Correlator
  12 Sep 2017 3 repositories listed
  Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking.
• SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network
  25 Jun 2025 2 repositories listed
  Human Activity Recognition (HAR), which uses data from Inertial Measurement Unit (IMU) sensors, has many practical applications in healthcare and assisted living environments.
• milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
  29 Jun 2023 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  In this work, we propose milliFlow, a novel deep learning approach to estimate scene flow as complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting…
• Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
  23 Jun 2023 2 repositories listed
  In this paper, we propose a novel strategy to combine publicly available datasets with the goal of learning a generalized HAR model that can be fine-tuned using a limited amount of labeled data on an unseen target…
• Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
  15 May 2023 2 repositories listed
  In this work, we focus on Few-Shot Domain Adaptation for Activity Recognition (FSDA-AR), which leverages a very small amount of labeled target videos to achieve effective adaptation.
• RHM: Robot House Multi-view Human Activity Recognition Dataset
  24 Apr 2023 2 repositories listed
  There are 14 classes with 6701 video clips for each view, making a total of 26804 video clips for the four views.
• IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text
  26 Oct 2022 2 repositories listed
  We present IMU2CLIP, a novel pre-training approach to align Inertial Measurement Unit (IMU) motion sensor recordings with video and text, by projecting them into the joint representation space of Contrastive…
• SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing
  16 Jul 2022 2 repositories listed Syntology ran 3 of 12 samples · 9 unverified
  WiFi sensing has been evolving rapidly in recent years.
• Defending Black-box Skeleton-based Human Activity Classifiers
  9 Mar 2022 2 repositories listed
  Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary…
• Transformer Networks for Data Augmentation of Human Physical Activity Recognition
  2 Sep 2021 2 repositories listed
  It improves generalization and reduces amount of annotated human activity data needed for training which reduces labour and time needed with the dataset.
• Spatio-Temporal Dynamic Inference Network for Group Activity Recognition
  26 Aug 2021 2 repositories listed Syntology ran 1 of 12 samples · 11 unverified
  Within each interaction field, we apply DR to predict the relation matrix and DW to predict the dynamic walk offsets in a joint-processing manner, thus forming a person-specific interaction graph.
• AdaRNN: Adaptive Learning and Forecasting of Time Series
  10 Aug 2021 2 repositories listed
  This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data.
• B-HAR: an open-source baseline framework for in depth study of human activity recognition datasets and workflows
  23 Jan 2021 2 repositories listed
  Human Activity Recognition (HAR), based on machine and deep learning algorithms is considered one of the most promising technologies to monitor professional and daily life activities for different categories of people…

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.