Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling
By Yu-Gang Jiang, Qi Dai, Wei David Liu, Xiangyang Xue, Chong-Wah Ngo. 2015
76 citations recorded by the source corpus.
Human action recognition in unconstrained videos is a challenging problem with many applications. Most state-of-the-art approaches adopted the well-known bag-of-features representations, generated based on isolated local patches or patch trajectories, where motion patterns, such as object-object and object-background relationships are mostly discarded. In this paper, we propose a simple representation aiming at modeling these motion relationships. We adopt global and local reference points to explicitly characterize motion information, so that the final representation is more robust to camera movements, which widely exist in unconstrained videos. Our approach operates on the top of visual codewords generated on dense local patch trajectories, and therefore, does not require foreground-background separation, which is normally a critical and difficult step in modeling object relationships. Through an extensive set of experimental evaluations, we show that the proposed representation produces a very competitive performance on several challenging benchmark data sets. Further combining it with the standard bag-of-features or Fisher vector representations can lead to substantial improvements.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, background): “ACTION recognition is a very important research problem owing to its relevance to a wide range of applications, such as video surveillance, patient monitoring, robotics, human-machine interaction, etc [1]–[3].”
- EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition (2018, background): “They can be extracted from the single frame or consecutive frame sequence locally at spatiotemporal interest points [27] or densely sampled in the whole frame [28].”
- Learning Layer-Skippable Inference Network (2020, background): “Relatedly, research on fine-grained classification [20]–[25] has been drawing a lot of attention over the years.”
- Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics (2019, background): “Learning powerful spatio-temporal representations is the most fundamental deep learning problem for many video understanding tasks such as action recognition [4, 17, 26], action proposal and localization [5, 33, 34], video captioning [40, 42], etc.”
- Going deeper into action recognition: A survey (2016, unknown): “ow) 88.2 LSTM (Image + Opt Flow) 88.6 Fernando et al. (2015) Rank Pooling 63.7 73.7 Donahue et al. (2015) LRCN- Weighted Avnerage of RBG + Flow 82.9 Wu et al. (2015) Adaptive Multi-Stream Fusion 92.6 Jiang et al. (2015) TrajShape+TrajMF 48.4 78.5 55.2 80.6 TrajShape+TrajMF+Wang and Schmid (2013) 57.”