With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significanc...With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significance and practical application value.Therefore,it is necessary to summarize the current research and provide some reference for researchers in this field.This article conducted a detailed and in-depth analysis and summarized of relevant research and typical methods of visual question answering field.First,relevant background knowledge about VQA(Visual Question Answering)was introduced.Secondly,the issues and challenges of visual question answering were discussed,and at the same time,some promising discussion on the particular methodologies was given.Thirdly,the key sub-problems affecting visual question answering were summarized and analyzed.Then,the current commonly used data sets and evaluation indicators were summarized.Next,in view of the popular algorithms and models in VQA research,comparison of the algorithms and models was summarized and listed.Finally,the future development trend and conclusion of visual question answering were prospected.展开更多
We name colors of foods with great ease. This process is conventionalized through our cultures and our biological dictates. People identify food colors through words that are again highly constrained. Embodiment of ex...We name colors of foods with great ease. This process is conventionalized through our cultures and our biological dictates. People identify food colors through words that are again highly constrained. Embodiment of experience and perception deals with these constraints to make color term use a cognitively economical mechanism, keeping numbers of concepts in mind through categorial conceptualization in long term memory. The parallel process that puts together our linguistic and visual information, allows the individual to map a correspondence between the two frames. The result of this mapping is a ＂cognitive color＂ in long term color memory. This paper presents an experiment in triggering long term memory and the response results. The objective was to verify whether individuals＇ cognitive color of well known foods, both raw and cooked, that they had just identified with Natural Color System （NCS） color samples, would be predominantly a primary basic color term, a secondary basic color term, or a complete descriptive utterance. The name used to communicate a desired signification is accessed through the judgement of similarity and difference with a point of reference. In this case, the food color vantage represents the cognitive color remembered.展开更多
Cases of imperfect or non-model mimicry are common in plants and animals and challenge intuitive assumptions about the nature of directional selection on mimics. Many non-rewarding flower species do not mimic a partic...Cases of imperfect or non-model mimicry are common in plants and animals and challenge intuitive assumptions about the nature of directional selection on mimics. Many non-rewarding flower species do not mimic a particular species, but at- tract pollinators through ＇generalised food deception＇. Some predatory animals also attract pollinators by resembling flowers, perhaps the most well known, yet least well understood, is the orchid mantis Hymenopus coronatus. This praying mantis has been hypothesised to mimic a flower corolla and we have previously shown that it attracts and captures pollinating insects as prey. Predatory pollinator deception is relatively unstudied and whether this occurs through model mimicry or generalised food decep- tion in the orchid mantis is unknown. To test whether the orchid mantis mimics a specific model flower species we investigated similarities between its morphology and that of flowers in its natural habitat in peninsular Malaysia. Geometric morphometrics were used to compare the shape of mantis femoral lobes to flower petals. Physiological vision models were used to compare the colour of mantises and flowers from the perspective of bees, flies and birds. We did not find strong evidence for a specific model flower species for the orchid mantis. The mantis＇ colour and shape varied within the range of that exhibited by many flower pet- als rather than resembling one type in particular. We suggest that the orchid mantis resembles an average, or generalised flower-like stimulus. Thus predatory pollinator deception in the orchid mantis is likely to function as a form of generalised food deception, as opposed to model mimicry .展开更多
基金Project(61702063)supported by the National Natural Science Foundation of China。
文摘With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significance and practical application value.Therefore,it is necessary to summarize the current research and provide some reference for researchers in this field.This article conducted a detailed and in-depth analysis and summarized of relevant research and typical methods of visual question answering field.First,relevant background knowledge about VQA(Visual Question Answering)was introduced.Secondly,the issues and challenges of visual question answering were discussed,and at the same time,some promising discussion on the particular methodologies was given.Thirdly,the key sub-problems affecting visual question answering were summarized and analyzed.Then,the current commonly used data sets and evaluation indicators were summarized.Next,in view of the popular algorithms and models in VQA research,comparison of the algorithms and models was summarized and listed.Finally,the future development trend and conclusion of visual question answering were prospected.
文摘We name colors of foods with great ease. This process is conventionalized through our cultures and our biological dictates. People identify food colors through words that are again highly constrained. Embodiment of experience and perception deals with these constraints to make color term use a cognitively economical mechanism, keeping numbers of concepts in mind through categorial conceptualization in long term memory. The parallel process that puts together our linguistic and visual information, allows the individual to map a correspondence between the two frames. The result of this mapping is a ＂cognitive color＂ in long term color memory. This paper presents an experiment in triggering long term memory and the response results. The objective was to verify whether individuals＇ cognitive color of well known foods, both raw and cooked, that they had just identified with Natural Color System （NCS） color samples, would be predominantly a primary basic color term, a secondary basic color term, or a complete descriptive utterance. The name used to communicate a desired signification is accessed through the judgement of similarity and difference with a point of reference. In this case, the food color vantage represents the cognitive color remembered.
文摘Cases of imperfect or non-model mimicry are common in plants and animals and challenge intuitive assumptions about the nature of directional selection on mimics. Many non-rewarding flower species do not mimic a particular species, but at- tract pollinators through ＇generalised food deception＇. Some predatory animals also attract pollinators by resembling flowers, perhaps the most well known, yet least well understood, is the orchid mantis Hymenopus coronatus. This praying mantis has been hypothesised to mimic a flower corolla and we have previously shown that it attracts and captures pollinating insects as prey. Predatory pollinator deception is relatively unstudied and whether this occurs through model mimicry or generalised food decep- tion in the orchid mantis is unknown. To test whether the orchid mantis mimics a specific model flower species we investigated similarities between its morphology and that of flowers in its natural habitat in peninsular Malaysia. Geometric morphometrics were used to compare the shape of mantis femoral lobes to flower petals. Physiological vision models were used to compare the colour of mantises and flowers from the perspective of bees, flies and birds. We did not find strong evidence for a specific model flower species for the orchid mantis. The mantis＇ colour and shape varied within the range of that exhibited by many flower pet- als rather than resembling one type in particular. We suggest that the orchid mantis resembles an average, or generalised flower-like stimulus. Thus predatory pollinator deception in the orchid mantis is likely to function as a form of generalised food deception, as opposed to model mimicry .
