 |
 |
 |
 |
 |
 |
||
 |
 |
 |
 |
 |
| 查看: 3494 | 回復(fù): 18 | |||
smallbug2000木蟲(chóng) (著名寫(xiě)手)
|
[求助]
哥的論文大修，哥很郁悶，哥不想改了
|
||
|
投了一篇論文到計(jì)算機(jī)視覺(jué)相關(guān)的雜志，最近返回結(jié)果，三個(gè)審稿人，其中兩個(gè)審稿人意見(jiàn)較少。另一個(gè)覺(jué)得算法的創(chuàng)新性不夠，給了大修，悲劇的是這篇論文之前投到CVPR去，也是這個(gè)審稿人審的（CVPR據(jù)了我），因?yàn)閷徃逡庖?jiàn)基本一樣，故可以斷定是同一審稿人。最終編輯給了大修，但是我很絕望，因?yàn)榻o大修的審稿人從一開(kāi)始就不認(rèn)可我的算法，我想既然我認(rèn)真修改了，可能還是會(huì)被他據(jù)。將編輯及大修審稿人意見(jiàn)附后，在此向各位大牛咨詢(xún)兩件事：1）該論文是否值得大修，修后被據(jù)的概率多大？2）如果大修，如果對(duì)付審稿人這么尖銳的問(wèn)題。在些感謝，對(duì)于好的建議發(fā)放金幣。 Dear**, Reviewers have now commented on your paper. You will see that they are advising that you revise your manuscript. If you are prepared to undertake the work required, I would be pleased to reconsider my decision. The reviewers' comments can be found at the end of this email or can be accessed by following the provided link. Reviewers' comments: The paper was reviewed by three experts on the topic. The reviewers agree that the paper discusses an important problem worth pursuing. They, however, also unanimously point out short comings of the paper, most important of which is the lack of thorough theoretical and experimental validation of the claims as well as references to prior work. The paper needs major revision to be considered for publication. If the authors decide to submit a major revision, please make sure to address the points raised by the reviewers. Reviewer #2: : This paper deals with the problem of visual tracking with irregular object motion. The particle set shift approach based on analytic optimization is proposed to deal with the incorrect state dynamic model. Particles are first sampled by the state dynamic model and they are moved to higher likelihood regions by newton optimization by maximizing likelihoods. The efficacy of the proposed approach is demonstrated via experiments with real sequences. - Positive points: Practically effective approach - Negative points: Not novel approach, rather heuristic, not convincing experimental results : The main problem of this paper is the proposed approach is not novel. The proposed approach is quite similar to [18] except the fact that the proposed approach used newton optimization instead of mean shift. : The proposed approach is rather heuristic. In the algorithm, particle weights are only proportional to likelihood, and this holds true for SIR particle filter where particles are sampled from state dynamic model. However, since particles are moved to higher likelihoods artificially, the weights determined from likelihoods will no longer correctly represent the true posterior. The proposed approach is rather similar to the particle swarm optimization-based tracking, e.g., "" by X. ** et al in CVPR 2008. Another problem of the proposed approach is that it might result in worse tracking results when there are appearance changes caused by various issues such as pose and lighting changes. : Since the proposed work is based on particle filter, the optimal importance functions used for visual tracking are also relevant. If we can use the optimal importance function, the irregular motion can be handled at least partially. Thus the following papers should be cited and commented as related work: - : The supplementary video result is too limited. Only a result for a single short sequence is not sufficient to support the validity of the proposed approach. Why is there no rotational motion in the results? The paper says that the state is translation, scale, and rotation, but there is no rotational motion in the results in the paper and video. : There must be cases that all particles are outside the basin of convergence. Since the particle are shifted by local optimization, particles will diverge from the optimal positions and tracking will fail. In the proposed approach, there is no consideration of this possibility. : The optimization will increase the computational complexity considerably. It is necessary to compare the other algorithms under the same computational time, e.g., proposed framework with 100 particles and standard particle filter with 1000 particles. My current recommendation is major revision. If the authors want to make the paper accepted in spite of the limited novelty and contribution, I think the followings should be addressed in the revision: - Additional experiments with object appearance changes like illumination - Addition of a mechanism to deal with the local optima problems with additional experiments with related videos - Comparison under the same computational complexity for different tracking algorithms [ Last edited by smallbug2000 on 2012-9-6 at 09:52 ] |
回復(fù)此樓» 收錄本帖的淘帖專(zhuān)輯推薦
 文章寫(xiě)作 |
» 猜你喜歡
考研調(diào)劑
已經(jīng)有3人回復(fù)
-
317分 一志愿南理工材料工程 本科湖工大 求調(diào)劑
已經(jīng)有9人回復(fù)
-
297求調(diào)劑
已經(jīng)有10人回復(fù)
-
一志愿武漢理工，總分321，英一數(shù)二，求老師收留。
已經(jīng)有10人回復(fù)
-
343求調(diào)劑
已經(jīng)有5人回復(fù)
-
085601材料工程找調(diào)劑
已經(jīng)有7人回復(fù)
-
求調(diào)劑，一志愿 南京航空航天大學(xué) ，080500材料科學(xué)與工程學(xué)碩，總分289分
已經(jīng)有6人回復(fù)
-
一志愿南航 335分 | 0856 | GPA 4.07 | 有科研經(jīng)歷
已經(jīng)有5人回復(fù)
-
340求調(diào)劑
已經(jīng)有5人回復(fù)
-
一志愿北化求調(diào)劑
已經(jīng)有4人回復(fù)
» 本主題相關(guān)價(jià)值貼推薦，對(duì)您同樣有幫助:
- 哥一直修改論文到現(xiàn)在
已經(jīng)有29人回復(fù)
- 修改意見(jiàn)是小修還是大修？已經(jīng)又返回去外審了，不懂！求教！
已經(jīng)有9人回復(fù)
- 還是reject and resubmitted
已經(jīng)有8人回復(fù)
- SCI論文大修意見(jiàn)中有一條修改意見(jiàn)不知道理解的對(duì)不對(duì)，請(qǐng)高手幫看看
已經(jīng)有11人回復(fù)
- 文章從major revision到 reject and resubmitted怎么回事？
已經(jīng)有16人回復(fù)
- 不想按評(píng)審意見(jiàn)全部重寫(xiě)一遍，后果怎樣
已經(jīng)有10人回復(fù)
- JMCA投稿后大修，返回修改稿后收到郵件，不懂什么意思啊，求大神幫忙
已經(jīng)有8人回復(fù)
- BMCL文章大修，不是很理解審稿意見(jiàn)，求指導(dǎo)從哪個(gè)角度進(jìn)行文章修改
已經(jīng)有6人回復(fù)
- 這個(gè)算是大改還是小改？
已經(jīng)有7人回復(fù)
- 論文第二次讓大修！
已經(jīng)有20人回復(fù)
- 同一篇論文連續(xù)第三次給大修有沒(méi)有��？
已經(jīng)有24人回復(fù)
- 論文一審回來(lái)后，大修，但是想更換些好的實(shí)驗(yàn)數(shù)據(jù)，可否？
已經(jīng)有5人回復(fù)
- SCI文章大修,四個(gè)審稿人,有一個(gè)不同意發(fā)表,大修返回后,據(jù)的這個(gè)審稿人態(tài)度會(huì)改變嗎
已經(jīng)有15人回復(fù)
- 請(qǐng)教：論文大修，機(jī)會(huì)大不大？三個(gè)月修改期限，多長(zhǎng)時(shí)間提交修改稿較好？謝謝！
已經(jīng)有11人回復(fù)
- 稿件被編輯婉拒后，還可以再投給該期刊的其他編輯嗎？
已經(jīng)有19人回復(fù)
- 論文大修 郁悶
已經(jīng)有19人回復(fù)
- 被一個(gè)雜志據(jù)稿，但是編輯說(shuō)按照要求修改可以重投稿，如何回編輯的信件？
已經(jīng)有8人回復(fù)
- 文章大修，修改期限降至，能不能向主編申請(qǐng)延期上交修改稿件？
已經(jīng)有6人回復(fù)
- 論文被拒，編輯意見(jiàn)改后重投
已經(jīng)有15人回復(fù)
- 請(qǐng)問(wèn)這種情況是大修還是小修，另外reviewer的建議需不需要改？
已經(jīng)有7人回復(fù)
- 文章大修，修改列表需要重復(fù)point-to-point 的修改細(xì)節(jié)嗎？
已經(jīng)有8人回復(fù)
- 論文大修，問(wèn)題一大堆，修改意見(jiàn)四頁(yè)多，修后錄用可能性大不？
已經(jīng)有30人回復(fù)
flywithyu
銅蟲(chóng) (小有名氣)
- 應(yīng)助: 6 (幼兒園)
- 金幣: 103.8
- 帖子: 82
- 在線: 17.6小時(shí)
- 蟲(chóng)號(hào): 1630735
- 注冊(cè): 2012-02-21
- 專(zhuān)業(yè): 信息處理方法與技術(shù)
【答案】應(yīng)助回帖
★ ★ ★ ★ ★ ★ ★ ★ ★ ★
感謝參與，應(yīng)助指數(shù) +1
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 14:45:35
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 17:37:34
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-11 19:27:09
smallbug2000: 金幣+4, ★★★★★最佳答案 2012-09-13 14:47:15
感謝參與，應(yīng)助指數(shù) +1
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 14:45:35
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 17:37:34
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-11 19:27:09
smallbug2000: 金幣+4, ★★★★★最佳答案 2012-09-13 14:47:15
|
這個(gè)修改意見(jiàn)不算多的，具體就是： 1、增加實(shí)驗(yàn)結(jié)果以驗(yàn)證你方法的有效性；（這個(gè)只要有數(shù)據(jù)，應(yīng)該好辦） 2、局部最優(yōu)問(wèn)題，這個(gè)較難回答，一種你找到方法；另外一種就是通過(guò)實(shí)驗(yàn)來(lái)說(shuō)明； 3、與不同算法的比較。首先找找網(wǎng)上有沒(méi)有現(xiàn)成的能出結(jié)果的代碼吧；實(shí)在不行只有自己實(shí)現(xiàn)；話說(shuō)實(shí)驗(yàn)室如果有做換個(gè)方向的話應(yīng)該是有一定基礎(chǔ)吧。 強(qiáng)烈建議：按照專(zhuān)家意見(jiàn)修改，不要回避，最終你會(huì)發(fā)現(xiàn)有收獲的！！  |
3樓2012-09-06 12:27:52
wangzhipengj
至尊木蟲(chóng) (文壇精英)
- 應(yīng)助: 240 (大學(xué)生)
- 金幣: 21356.1
- 散金: 5
- 紅花: 43
- 帖子: 10888
- 在線: 551.1小時(shí)
- 蟲(chóng)號(hào): 1702123
- 注冊(cè): 2012-03-19
- 專(zhuān)業(yè): 高分子合成化學(xué)
4樓2012-09-06 13:05:39
★ ★
感謝參與，應(yīng)助指數(shù) +1
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 17:27:12
感謝參與，應(yīng)助指數(shù) +1
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 17:27:12
|
本帖內(nèi)容被屏蔽 |
6樓2012-09-06 15:55:48
flywithyu
銅蟲(chóng) (小有名氣)
- 應(yīng)助: 6 (幼兒園)
- 金幣: 103.8
- 帖子: 82
- 在線: 17.6小時(shí)
- 蟲(chóng)號(hào): 1630735
- 注冊(cè): 2012-02-21
- 專(zhuān)業(yè): 信息處理方法與技術(shù)
|
哦，沒(méi)有仔細(xì)看，是的，是比較計(jì)算復(fù)雜度  我曾經(jīng)有篇文章，3個(gè)審稿人都提了若干條修改意見(jiàn)；其中一個(gè)估計(jì)是老外，看的非常仔細(xì)，提了9條意見(jiàn)，每條都很頭疼。 硬著頭皮逐條對(duì)照修改，實(shí)在改不了或者實(shí)現(xiàn)起來(lái)有難度，也一定要能說(shuō)服審稿人。 最后改完，3人全部通過(guò)。不過(guò)等于是重寫(xiě)了篇。。。 還是那句話，審稿人提的意見(jiàn)一般都是很中肯的，建議對(duì)照修改，而不是降低檔次改投別的。。 |
10樓2012-09-06 20:54:39
carsonwen
銅蟲(chóng) (小有名氣)
- 應(yīng)助: 1 (幼兒園)
- 金幣: 177.4
- 散金: 10
- 帖子: 71
- 在線: 11.6小時(shí)
- 蟲(chóng)號(hào): 44277
- 注冊(cè): 2004-04-24
- 性別: GG
- 專(zhuān)業(yè): 信息處理方法與技術(shù)
2樓2012-09-06 10:30:45
寒山聽(tīng)雪
鐵蟲(chóng) (小有名氣)
- 應(yīng)助: 4 (幼兒園)
- 金幣: 67.2
- 散金: 14
- 帖子: 80
- 在線: 24.3小時(shí)
- 蟲(chóng)號(hào): 1894930
- 注冊(cè): 2012-07-16
- 性別: GG
- 專(zhuān)業(yè): 生物信息學(xué)
5樓2012-09-06 15:42:20
wygvern
木蟲(chóng) (職業(yè)作家)
- 應(yīng)助: 6 (幼兒園)
- 金幣: 3703.9
- 散金: 100
- 紅花: 3
- 帖子: 3287
- 在線: 170.3小時(shí)
- 蟲(chóng)號(hào): 996070
- 注冊(cè): 2010-04-13
- 性別: GG
- 專(zhuān)業(yè): 控制理論與方法
7樓2012-09-06 16:47:13
smallbug2000
木蟲(chóng) (著名寫(xiě)手)
- 應(yīng)助: 13 (小學(xué)生)
- 金幣: 2299.8
- 散金: 1794
- 紅花: 17
- 帖子: 1239
- 在線: 782小時(shí)
- 蟲(chóng)號(hào): 434011
- 注冊(cè): 2007-08-18
- 性別: GG
- 專(zhuān)業(yè): 計(jì)算機(jī)應(yīng)用技術(shù)
8樓2012-09-06 17:26:40
smallbug2000
木蟲(chóng) (著名寫(xiě)手)
- 應(yīng)助: 13 (小學(xué)生)
- 金幣: 2299.8
- 散金: 1794
- 紅花: 17
- 帖子: 1239
- 在線: 782小時(shí)
- 蟲(chóng)號(hào): 434011
- 注冊(cè): 2007-08-18
- 性別: GG
- 專(zhuān)業(yè): 計(jì)算機(jī)應(yīng)用技術(shù)
9樓2012-09-06 18:53:30
相關(guān)版塊跳轉(zhuǎn)
我要訂閱樓主 smallbug2000 的主題更新
| 最具人氣熱帖推薦 [查看全部] | 作者 | 回/看 | 最后發(fā)表 | |
|---|---|---|---|---|
|
[考研] 317分 一志愿南理工材料工程 本科湖工大 求調(diào)劑 +9 | 芋泥小鈴鐺 2026-03-28 | 9/450 |
|
|---|---|---|---|---|
|
[考研] 332求調(diào)劑 +8 | 蕉蕉123 2026-03-28 | 8/400 |
|
|
|
[考研] 0856材料化工調(diào)劑 總分330 +14 | zhubinhao 2026-03-27 | 14/700 |
|
|
|
[考研] 調(diào)劑310 +8 | 溫柔的晚安 2026-03-25 | 9/450 |
|
|
|
[考研] 085600 材料與化工 329分求調(diào)劑 +11 | Mr. Z 2026-03-25 | 11/550 |
|
|
|
[考研] 一志愿哈爾濱工業(yè)大學(xué)材料與化工方向336分 +9 | 辰沐5211314 2026-03-26 | 9/450 |
|
|
|
[考研] 一志愿北化085600材料專(zhuān)碩275|有文章專(zhuān)利｜求調(diào)劑 +7 | Micky11223 2026-03-25 | 7/350 |
|
|
|
[考研] 085602 化工專(zhuān)碩 338分 求調(diào)劑 +12 | 路癡小琪 2026-03-27 | 12/600 |
|
|
|
[考研] 394求調(diào)劑 +3 | 好事多磨靜候佳?/a> 2026-03-26 | 5/250 |
|
|
|
[考研] 286求調(diào)劑 +12 | PolarBear11 2026-03-26 | 12/600 |
|
|
|
[考研] 085602 307分 求調(diào)劑 +7 | 不知道叫什么！ 2026-03-26 | 7/350 |
|
|
|
[考博] 26申博 +3 | 加油沖�。� 2026-03-26 | 3/150 |
|
|
|
[考研] 307求調(diào)劑 +8 | 超級(jí)伊昂大王 2026-03-24 | 9/450 |
|
|
|
[考研]
材料學(xué)碩，求調(diào)劑
 6+5
|
糖葫蘆888ll 2026-03-22 | 10/500 |
|
|
|
[考研] 一志愿 南京郵電大學(xué) 288分 材料考研 求調(diào)劑 +3 | jl0720 2026-03-26 | 3/150 |
|
|
|
[考研] 總分293求調(diào)劑 +6 | 加一一九 2026-03-25 | 8/400 |
|
|
|
[考研] 一志愿吉林大學(xué)材料與化工303分求調(diào)劑 +4 | 為學(xué)666 2026-03-24 | 4/200 |
|
|
|
[考研] 一志愿武理085500機(jī)械專(zhuān)業(yè)總分300求調(diào)劑 +3 | an10101 2026-03-24 | 7/350 |
|
|
|
[考研] 調(diào)劑 +4 | 13853210211 2026-03-24 | 4/200 |
|
|
|
[考研] 292求調(diào)劑 +4 | 鵝鵝鵝額額額額?/a> 2026-03-24 | 4/200 |
|