Zero-Shot Action Recognition With Error-Correcting Output Codes
Recently, zero-shot action recognition (ZSAR) has emerged with the explosive growth of action categories. In this paper, we explore ZSAR from a novel perspective by adopting the Error-Correcting Output Codes (dubbed ZSECOC). Our ZSECOC equips the conventional ECOC with the additional capability of ZSAR, by addressing the domain shift problem. In particular, we learn discriminative ZSECOC for seen categories from both category-level semantics and intrinsic data structures. This procedure deals with domain shift implicitly by transferring the well-established correlations among seen categories to unseen ones. Moreover, a simple semantic transfer strategy is developed for explicitly transforming the learned embeddings of seen categories to better fit the underlying structure of unseen categories. As a consequence, our ZSECOC inherits the promising characteristics from ECOC as well as overcomes domain shift, making it more discriminative for ZSAR. We systematically evaluate ZSECOC on three realistic action benchmarks, i.e. Olympic Sports, HMDB51 and UCF101. The experimental results clearly show the superiority of ZSECOC over the state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionTemporal Action LocalizationZero-Shot Action RecognitionSimilar Papers 제목 키워드 기반
Large Language Models based ASR Error Correction for Child Conversations
Automatic Speech Recognition (ASR) has recently shown remarkable progress, but accurately transcribing children's speech remains a significant challenge. Recent developments in Large Language Models (LLMs) have shown pro…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionZero-shot Faithful Factual Error Correction
Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge bases and preventing hallucinations in sequence-to-sequence models. Drawing on humans' ability to identify and correct f…
A New Split for Evaluating True Zero-Shot Action Recognition
Zero-shot action recognition is the task of classifying action categories that are not available in the training set. In this setting, the standard evaluation protocol is to use existing action recognition datasets(e.g. …
Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionZero-Shot Action Recognition+1DiZiNER: Disagreement-guided Instruction Refinement via Pilot Annotation Simulation for Zero-shot Named Entity Recognition
Large language models (LLMs) have advanced information extraction (IE) by enabling zero-shot and few-shot named entity recognition (NER), yet their generative outputs still show persistent and systematic errors. Despite …
Information ExtractionTARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
In this paper we propose a novel Temporal Attentive Relation Network (TARN) for the problems of few-shot and zero-shot action recognition. At the heart of our network is a meta-learning approach that learns to compare re…
Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionMeta-Learning+4