PyTorchKR Papers

최신 논문

총 38편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2212.04119공식 코드 · Papers with Code

DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset

As sharing images in an instant message is a crucial factor, there has been active research on learning an image-text multi-modal dialogue models. However, training a well-generalized multi-modal dialogue model remains challenging due to the low quality and limited diversity of images per dialogue in existing multi-modal dialogue datasets. In this paper, we propose an automated pipeline to construct a multi-modal dialogue dataset, ensuring both dialogue quality and image diversity without requiring minimum human effort. In our pipeline, to guarantee the coherence between images and dialogue, we prompt GPT-4 to infer potential image-sharing moments - specifically, the utterance, speaker, rationale, and image description. Furthermore, we leverage CLIP similarity to maintain consistency between aligned multiple images to the utterance. Through this pipeline, we introduce DialogCC, a high-quality and diverse multi-modal dialogue dataset that surpasses existing datasets in terms of quality and diversity in human evaluation. Our comprehensive experiments highlight that when multi-modal dialogue models are trained using our dataset, their generalization performance on unseen dialogue datasets is significantly enhanced. We make our source code and dataset publicly available.

arXiv:2210.11109공식 코드 · Papers with Code

Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation

Image-to-text tasks, such as open-ended image captioning and controllable image description, have received extensive attention for decades. Here, we further advance this line of work by presenting Visual Spatial Description (VSD), a new perspective for image-to-text toward spatial semantics. Given an image and two objects inside it, VSD aims to produce one description focusing on the spatial perspective between the two objects. Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones. In addition, we investigate pipeline and joint end-to-end architectures for incorporating visual spatial relationship classification (VSRC) information into our model. Finally, we conduct experiments on our benchmark dataset to evaluate all our models. Results show that our models are impressive, providing accurate and human-like spatial-oriented text descriptions. Meanwhile, VSRC has great potential for VSD, and the joint end-to-end architecture is the better choice for their integration. We make the dataset and codes public for research purposes.

arXiv:2210.04754공식 코드 · Papers with Code

Improving Visual-Semantic Embeddings by Learning Semantically-Enhanced Hard Negatives for Cross-modal Information Retrieval

Visual Semantic Embedding (VSE) aims to extract the semantics of images and their descriptions, and embed them into the same latent space for cross-modal information retrieval. Most existing VSE networks are trained by adopting a hard negatives loss function which learns an objective margin between the similarity of relevant and irrelevant image-description embedding pairs. However, the objective margin in the hard negatives loss function is set as a fixed hyperparameter that ignores the semantic differences of the irrelevant image-description pairs. To address the challenge of measuring the optimal similarities between image-description pairs before obtaining the trained VSE networks, this paper presents a novel approach that comprises two main parts: (1) finds the underlying semantics of image descriptions; and (2) proposes a novel semantically enhanced hard negatives loss function, where the learning objective is dynamically determined based on the optimal similarity scores between irrelevant image-description pairs. Extensive experiments were carried out by integrating the proposed methods into five state-of-the-art VSE networks that were applied to three benchmark datasets for cross-modal information retrieval tasks. The results revealed that the proposed methods achieved the best performance and can also be adopted by existing and future VSE networks.

arXiv:2207.05493공식 코드 · Papers with Code

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph Convolutional Networks, the local attention mask is defined based on natural connections of human skeleton joints and ignores the dynamic relations for example between head, hands and feet joints. In addition, the attention mechanism has been proven effective in Natural Language Processing and image description, which is rarely investigated in existing methods. In this work, we proposed a new adaptive spatial attention layer that extends local attention map to global based on relative distance and relative angle information. Moreover, we design a new initial graph adjacency matrix that connects head, hands and feet, which shows visible improvement in terms of action recognition accuracy. The proposed model is evaluated on two large-scale and challenging datasets in the field of human activities in daily life: NTU-RGB+D and Kinetics skeleton. The results demonstrate that our model has strong performance on both dataset.

arXiv:2111.12085공식 코드 · Papers with Code

UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling

We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text description and align predicted words with object regions. To achieve this, models must generate desired text and box outputs together, and meanwhile indicate the alignments between words and boxes. In contrast to existing solutions that use multiple separate modules for different outputs, UniTAB represents both text and box outputs with a shared token sequence, and introduces a special <obj> token to naturally indicate word-box alignments in the sequence. UniTAB thus could provide a more comprehensive and interpretable image description, by freely grounding generated words to object regions. On grounded captioning, UniTAB presents a simpler solution with a single output head, and significantly outperforms state of the art in both grounding and captioning evaluations. On general VL tasks that have different desired output formats (i.e., text, box, or their combination), UniTAB with a single network achieves better or comparable performance than task-specific state of the art. Experiments cover 7 VL benchmarks, including grounded captioning, visual grounding, image captioning, and visual question answering. Furthermore, UniTAB's unified multi-task network and the task-agnostic output sequence design make the model parameter efficient and generalizable to new tasks.

arXiv:2109.13701공식 코드 · Papers with Code

CIDEr-R: Robust Consensus-based Image Description Evaluation

This paper shows that CIDEr-D, a traditional evaluation metric for image description, does not work properly on datasets where the number of words in the sentence is significantly greater than those in the MS COCO Captions dataset. We also show that CIDEr-D has performance hampered by the lack of multiple reference sentences and high variance of sentence length. To bypass this problem, we introduce CIDEr-R, which improves CIDEr-D, making it more flexible in dealing with datasets with high sentence length variance. We demonstrate that CIDEr-R is more accurate and closer to human judgment than CIDEr-D; CIDEr-R is more robust regarding the number of available references. Our results reveal that using Self-Critical Sequence Training to optimize CIDEr-R generates descriptive captions. In contrast, when CIDEr-D is optimized, the generated captions' length tends to be similar to the reference length. However, the models also repeat several times the same word to increase the sentence length.

arXiv:2109.02748공식 코드 · Papers with Code

Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP

In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their respective classes and also (2) detect samples that do not belong to any of the known classes (i.e., they belong to some unknown or OOD classes). This paper studies the problem of zero-shot out-of-distribution(OOD) detection, which still performs the same two tasks in testing but has no training except using the given known class names. This paper proposes a novel yet simple method (called ZOC) to solve the problem. ZOC builds on top of the recent advances in zero-shot classification through multi-modal representation learning. It first extends the pre-trained language-vision model CLIP by training a text-based image description generator on top of CLIP. In testing, it uses the extended model to generate candidate unknown class names for each test sample and computes a confidence score based on both the known class names and candidate unknown class names for zero-shot OOD detection. Experimental results on 5 benchmark datasets for OOD detection demonstrate that ZOC outperforms the baselines by a large margin.

arXiv:2108.08380공식 코드 · Papers with Code

Revisiting Binary Local Image Description for Resource Limited Devices

The advent of a panoply of resource limited devices opens up new challenges in the design of computer vision algorithms with a clear compromise between accuracy and computational requirements. In this paper we present new binary image descriptors that emerge from the application of triplet ranking loss, hard negative mining and anchor swapping to traditional features based on pixel differences and image gradients. These descriptors, BAD (Box Average Difference) and HashSIFT, establish new operating points in the state-of-the-art's accuracy vs.\ resources trade-off curve. In our experiments we evaluate the accuracy, execution time and energy consumption of the proposed descriptors. We show that BAD bears the fastest descriptor implementation in the literature while HashSIFT approaches in accuracy that of the top deep learning-based descriptors, being computationally more efficient. We have made the source code public.

arXiv:2011.04592공식 코드 · Papers with Code

Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze

When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting point a state-of-the-art image captioning system and develop several model variants that exploit information from human gaze patterns recorded during language production. In particular, we propose the first approach to image description generation where visual processing is modelled $\textit{sequentially}$. Our experiments and analyses confirm that better descriptions can be obtained by exploiting gaze-driven attention and shed light on human cognitive processes by comparing different ways of aligning the gaze modality with language production. We find that processing gaze data sequentially leads to descriptions that are better aligned to those produced by speakers, more diverse, and more natural${-}$particularly when gaze is encoded with a dedicated recurrent component.

arXiv:1911.03738공식 코드 · Papers with Code

On Architectures for Including Visual Information in Neural Language Models for Image Description

A neural language model can be conditioned into generating descriptions for images by providing visual information apart from the sentence prefix. This visual information can be included into the language model through different points of entry resulting in different neural architectures. We identify four main architectures which we call init-inject, pre-inject, par-inject, and merge. We analyse these four architectures and conclude that the best performing one is init-inject, which is when the visual information is injected into the initial state of the recurrent neural network. We confirm this using both automatic evaluation measures and human annotation. We then analyse how much influence the images have on each architecture. This is done by measuring how different the output probabilities of a model are when a partial sentence is combined with a completely different image from the one it is meant to be combined with. We find that init-inject tends to quickly become less influenced by the image as more words are generated. A different architecture called merge, which is when the visual information is merged with the recurrent neural network's hidden state vector prior to output, loses visual influence much more slowly, suggesting that it would work better for generating longer sentences. We also observe that the merge architecture can have its recurrent neural network pre-trained in a text-only language model (transfer learning) rather than be initialised randomly as usual. This results in even better performance than the other architectures, provided that the source language model is not too good at language modelling or it will overspecialise and be less effective at image description generation. Our work opens up new avenues of research in neural architectures, explainable AI, and transfer learning.

arXiv:1812.06587공식 코드 · Papers with Code

Grounded Video Description

Video description is one of the most challenging problems in vision and language understanding due to the large variability both on the video and language side. Models, hence, typically shortcut the difficulty in recognition and generate plausible sentences that are based on priors but are not necessarily grounded in the video. In this work, we explicitly link the sentence to the evidence in the video by annotating each noun phrase in a sentence with the corresponding bounding box in one of the frames of a video. Our dataset, ActivityNet-Entities, augments the challenging ActivityNet Captions dataset with 158k bounding box annotations, each grounding a noun phrase. This allows training video description models with this data, and importantly, evaluate how grounded or "true" such model are to the video they describe. To generate grounded captions, we propose a novel video description model which is able to exploit these bounding box annotations. We demonstrate the effectiveness of our model on our dataset, but also show how it can be applied to image description on the Flickr30k Entities dataset. We achieve state-of-the-art performance on video description, video paragraph description, and image description and demonstrate our generated sentences are better grounded in the video.

arXiv:1502.08029공식 코드 · Papers with Code

Describing Videos by Exploiting Temporal Structure

Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural language description. In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions. First, our approach incorporates a spatial temporal 3-D convolutional neural network (3-D CNN) representation of the short temporal dynamics. The 3-D CNN representation is trained on video action recognition tasks, so as to produce a representation that is tuned to human motion and behavior. Second we propose a temporal attention mechanism that allows to go beyond local temporal modeling and learns to automatically select the most relevant temporal segments given the text-generating RNN. Our approach exceeds the current state-of-art for both BLEU and METEOR metrics on the Youtube2Text dataset. We also present results on a new, larger and more challenging dataset of paired video and natural language descriptions.

arXiv:1603.09188공식 코드 · Papers with Code

Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings

We introduce a new task, visual sense disambiguation for verbs: given an image and a verb, assign the correct sense of the verb, i.e., the one that describes the action depicted in the image. Just as textual word sense disambiguation is useful for a wide range of NLP tasks, visual sense disambiguation can be useful for multimodal tasks such as image retrieval, image description, and text illustration. We introduce VerSe, a new dataset that augments existing multimodal datasets (COCO and TUHOI) with sense labels. We propose an unsupervised algorithm based on Lesk which performs visual sense disambiguation using textual, visual, or multimodal embeddings. We find that textual embeddings perform well when gold-standard textual annotations (object labels and image descriptions) are available, while multimodal embeddings perform well on unannotated images. We also verify our findings by using the textual and multimodal embeddings as features in a supervised setting and analyse the performance of visual sense disambiguation task. VerSe is made publicly available and can be downloaded at: https://github.com/spandanagella/verse.

arXiv:1605.00459공식 코드 · Papers with Code

Multi30K: Multilingual English-German Image Descriptions

We introduce the Multi30K dataset to stimulate multilingual multimodal research. Recent advances in image description have been demonstrated on English-language datasets almost exclusively, but image description should not be limited to English. This dataset extends the Flickr30K dataset with i) German translations created by professional translators over a subset of the English descriptions, and ii) descriptions crowdsourced independently of the original English descriptions. We outline how the data can be used for multilingual image description and multimodal machine translation, but we anticipate the data will be useful for a broader range of tasks.

arXiv:1606.06164공식 코드 · Papers with Code

Pragmatic factors in image description: the case of negations

We provide a qualitative analysis of the descriptions containing negations (no, not, n't, nobody, etc) in the Flickr30K corpus, and a categorization of negation uses. Based on this analysis, we provide a set of requirements that an image description system should have in order to generate negation sentences. As a pilot experiment, we used our categorization to manually annotate sentences containing negations in the Flickr30K corpus, with an agreement score of K=0.67. With this paper, we hope to open up a broader discussion of subjective language in image descriptions.

arXiv:1705.10739공식 코드 · Papers with Code

Efficient Decentralized Visual Place Recognition From Full-Image Descriptors

In this paper, we discuss the adaptation of our decentralized place recognition method described in [1] to full image descriptors. As we had shown, the key to making a scalable decentralized visual place recognition lies in exploting deterministic key assignment in a distributed key-value map. Through this, it is possible to reduce bandwidth by up to a factor of n, the robot count, by casting visual place recognition to a key-value lookup problem. In [1], we exploited this for the bag-of-words method [3], [4]. Our method of casting bag-of-words, however, results in a complex decentralized system, which has inherently worse recall than its centralized counterpart. In this paper, we instead start from the recent full-image description method NetVLAD [5]. As we show, casting this to a key-value lookup problem can be achieved with k-means clustering, and results in a much simpler system than [1]. The resulting system still has some flaws, albeit of a completely different nature: it suffers when the environment seen during deployment lies in a different distribution in feature space than the environment seen during training.

arXiv:1707.01736공식 코드 · Papers with Code

Cross-linguistic differences and similarities in image descriptions

Automatic image description systems are commonly trained and evaluated on large image description datasets. Recently, researchers have started to collect such datasets for languages other than English. An unexplored question is how different these datasets are from English and, if there are any differences, what causes them to differ. This paper provides a cross-linguistic comparison of Dutch, English, and German image descriptions. We find that these descriptions are similar in many respects, but the familiarity of crowd workers with the subjects of the images has a noticeable influence on description specificity.

arXiv:1806.00738공식 코드 · Papers with Code

Contextualize, Show and Tell: A Neural Visual Storyteller

We present a neural model for generating short stories from image sequences, which extends the image description model by Vinyals et al. (Vinyals et al., 2015). This extension relies on an encoder LSTM to compute a context vector of each story from the image sequence. This context vector is used as the first state of multiple independent decoder LSTMs, each of which generates the portion of the story corresponding to each image in the sequence by taking the image embedding as the first input. Our model showed competitive results with the METEOR metric and human ratings in the internal track of the Visual Storytelling Challenge 2018.