Related papers: TEACH: Text Encoding as Curriculum Hints for Scene…
Linguistic knowledge has brought great benefits to scene text recognition by providing semantics to refine character sequences. However, since linguistic knowledge has been applied individually on the output sequence, previous methods have…
A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the…
Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…
Reading text in the wild is a challenging task in the field of computer vision. Existing approaches mainly adopted Connectionist Temporal Classification (CTC) or Attention models based on Recurrent Neural Network (RNN), which is…
Emotion recognition in conversation (ERC) has emerged as a research hotspot in domains such as conversational robots and question-answer systems. How to efficiently and adequately retrieve contextual emotional cues has been one of the key…
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encoding function, mapping the ground-truth labels into latent…
Image classification has been studied extensively but there has been limited work in the direction of using non-conventional, external guidance other than traditional image-label pairs to train such models. In this thesis we present a set…
We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that…
Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…
Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared to diffusion-based methods. However, extending AR models to…
Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable…
Scene classification has established itself as a challenging research problem. Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of…
Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained with speech-text paired data. It is challenging to…
Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…
Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…
Temporal action segmentation in videos has drawn much attention recently. Timestamp supervision is a cost-effective way for this task. To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels…
Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting…
To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks. In this work, we present a simple…
End-to-end speech translation poses a heavy burden on the encoder, because it has to transcribe, understand, and learn cross-lingual semantics simultaneously. To obtain a powerful encoder, traditional methods pre-train it on ASR data to…
Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…