paper-with-me

홈 › Papers

Trajectory-aligned Space-time Tokens for Few-shot Action Recognition

2024-07-25 · Pulkit Kumar, Namitha Padmanabhan, Luke Luo, Sai Saketh Rambhatla, Abhinav Shrivastava

We propose a simple yet effective approach for few-shot action recognition, emphasizing the disentanglement of motion and appearance representations. By harnessing recent progress in tracking, specifically point trajectories and self-supervised representation learning, we build trajectory-aligned tokens (TATs) that capture motion and appearance information. This approach significantly reduces the data requirements while retaining essential information. To process these representations, we use a Masked Space-time Transformer that effectively learns to aggregate information to facilitate few-shot action recognition. We demonstrate state-of-the-art results on few-shot action recognition across multiple datasets. Our project page is available at https://www.cs.umd.edu/~pulkit/tats

📄 PDF Abstract BibTeX arXiv:2407.18249

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionDisentanglementFew-Shot action recognitionFew Shot Action RecognitionRepresentation Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition

2025-08-05 · Pulkit Kumar, Shuaiyi Huang, Matthew Walmer, Sai Saketh Rambhatla 외 arxiv

Video understanding requires effective modeling of both motion and appearance information, particularly for few-shot action recognition. While recent advances in point tracking have been shown to improve few-shot action …

Action RecognitionPoint Tracking

Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval

2024-03-24 · CVPR 2024 1 · Yucheng Suo, Fan Ma, Linchao Zhu, Yi Yang

We study the zero-shot Composed Image Retrieval (ZS-CIR) task, which is to retrieve the target image given a reference image and a description without training on the triplet datasets. Previous works generate pseudo-word…

AttributeImage RetrievalRetrievalTriplet+1

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

2026-05-06 · Huimin Wang, Yue Wang, Bihao Cui, Pengxiang Li 외 arxiv

We introduce ReflectDrive-2, a masked discrete diffusion planner with separate action expert for autonomous driving that represents plans as discrete trajectory tokens and generates them through parallel masked decoding.…

Reinforcement LearningAutonomous Driving

How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction

2026-05-19 · Sejoon Jun, Hai Nguyen-Truong, Luigi Seminara, Lorenzo Torresani arxiv

Predicting how a person's first-person view will evolve (what action will follow, what plan completes a task, whether an in-progress shot will score) is fundamentally under-specified: the same context admits many plausib…

Pose Estimation

Nudging: Inference-time Alignment of LLMs via Guided Decoding

2024-10-11 · Yu Fei, Yasaman Razeghi, Sameer Singh

Large language models (LLMs) require alignment to effectively and safely follow user instructions. This process necessitates training an aligned version for every base model, resulting in significant computational overhe…

General KnowledgeGSM8KInstruction Followingmodel