Related papers: Spatio-temporal Decoupled Knowledge Compensator fo…
Few-shot Action Recognition (FSAR) constitutes a crucial challenge in computer vision, entailing the recognition of actions from a limited set of examples. Recent approaches mainly focus on employing image-level features to construct…
In this paper, we propose a novel Temporal Sequence-Aware Model (TSAM) for few-shot action recognition (FSAR), which incorporates a sequential perceiver adapter into the pre-training framework, to integrate both the spatial information and…
Recent work on action recognition leverages 3D features and textual information to achieve state-of-the-art performance. However, most of the current few-shot action recognition methods still rely on 2D frame-level representations, often…
A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to…
Few-shot action recognition (FSAR) aims to learn a model capable of identifying novel actions in videos using only a few examples. In assuming the base dataset seen during meta-training and novel dataset used for evaluation can come from…
Few-shot action recognition aims to enable models to quickly learn new action categories from limited labeled samples, addressing the challenge of data scarcity in real-world applications. Current research primarily addresses three core…
Effectively modeling discriminative spatio-temporal information is essential for segmenting activities in long action sequences. However, we observe that existing methods are limited in weak spatio-temporal modeling capability due to two…
Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal…
Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level representations for each video by designing inter-frame temporal modeling strategies or…
Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal…
Few-shot action recognition (FSAR) has recently made notable progress through set matching and efficient adaptation of large-scale pre-trained models. However, two key limitations persist. First, existing set matching metrics typically rely…
High frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional…
Aligning egocentric video with wearable sensors have shown promise for human action recognition, but face practical limitations in user discomfort, privacy concerns, and scalability. We explore exocentric video with ambient sensors as a…
Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to…
Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment…
We propose a novel few-shot action recognition framework, STRM, which enhances class-specific feature discriminability while simultaneously learning higher-order temporal representations. The focus of our approach is a novel spatio-temporal…
Adapting pre-trained image models to video modality has proven to be an effective strategy for robust few-shot action recognition. In this work, we explore the potential of adapter tuning in image-to-video model adaptation and propose a…
Going beyond few-shot action recognition (FSAR), cross-domain FSAR (CDFSAR) has attracted recent research interests by solving the domain gap lying in source-to-target transfer learning. Existing CDFSAR methods mainly focus on joint…
Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual…
Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at…